To see the other types of publications on this topic, follow the link: Fire detection.
Journal articles on the topic 'Fire detection'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Fire detection.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Ramya Laxmi, K., A. Sreeja, E. Revanth, Manasa Gourishetty, and M. Rushikesh. "AUTOMATED FIRE DETECTION AND SURVEILLANCE SYSTEM." YMER Digital 21, no. 04 (April 24, 2022): 432–37. http://dx.doi.org/10.37896/ymer21.04/41.
Full textAbstract:
The major goal of this project is to build a fire detection and surveillance system that is automatic. During surveillance, Convolutional Neural Networks will be employed to detect the fire (CNNs). Such methods, on the other hand, typically need greater processing time and memory, limiting their use in surveillance networks. We propose a low-cost fire detection CNN architecture for surveillance films in this research. This is mostly concerned with computational complexity and detection precision. The model is fine-tuned to balance efficiency and accuracy, taking into account the nature of the target problem and fire data. This system takes an image or video file as input and detects fire and fire percentages that are precise enough to prevent fire mishaps and save human lives.
2
Dandge, Shrikant. "Survey on Fire Detection Using Image Processing." International Journal for Research in Applied Science and Engineering Technology 10, no. 11 (November 30, 2022): 2048–57. http://dx.doi.org/10.22214/ijraset.2022.47749.
Full textAbstract:
Abstract: With rising Urbanisation the frequency of fires has increased. A rapid need exists for quick and effective fire detection. Traditional fire detection systems are utilizing physical sensors to detect fire. Sensors gather information about the chemical characteristics of airborne particles, which traditional fire detection systems then use to generate an alarm. However, it can also result in false alerts; for instance, an ordinary fire alarm system might be triggered by smoking inside a space. Using a computer system based on vision for detecting fire would facilitate rapid and precise detection of fire with the ongoing developments in image processing. A lot of observable improvements have been developed to help a successful fire detection algorithm or model. This paper compiles research on methods that, when used, can effectively detect fire. In addition, a system architecture for fire detection is developed in this study. It suggests many fire detection methods, including Celik, SDD, F-RCNN, R-FCN and YOLOv3. This paper offers a thorough comparison of the same.
3
Le Maoult, Y., T. Sentenac, J. J. Orteu, and J. P. Arcens. "Fire Detection." Process Safety and Environmental Protection 85, no. 3 (January 2007): 193–206. http://dx.doi.org/10.1205/psep06035.
Full text
4
Lu, Xiaoman, Xiaoyang Zhang, Fangjun Li, Mark A. Cochrane, and Pubu Ciren. "Detection of Fire Smoke Plumes Based on Aerosol Scattering Using VIIRS Data over Global Fire-Prone Regions." Remote Sensing 13, no. 2 (January 8, 2021): 196. http://dx.doi.org/10.3390/rs13020196.
Full textAbstract:
Smoke from fires significantly influences climate, weather, and human health. Fire smoke is traditionally detected using an aerosol index calculated from spectral contrast changes. However, such methods usually miss thin smoke plumes. It also remains challenging to accurately separate smoke plumes from dust, clouds, and bright surfaces. To improve smoke plume detections, this paper presents a new scattering-based smoke detection algorithm (SSDA) depending mainly on visible and infrared imaging radiometer suite (VIIRS) blue and green bands. The SSDA is established based on the theory of Mie scattering that occurs when the diameter of an atmospheric particulate is similar to the wavelength of the scattered light. Thus, smoke commonly causes Mie scattering in VIIRS blue and green bands because of the close correspondence between smoke particulate diameters and the blue/green band wavelengths. For developing the SSDA, training samples were selected from global fire-prone regions in North America, South America, Africa, Indonesia, Siberia, and Australia. The SSDA performance was evaluated against the VIIRS aerosol detection product and smoke detections from the ultraviolet aerosol index using manually labeled fire smoke plumes as a benchmark. Results show that the SSDA smoke detections are superior to existing products due chiefly to the improved ability of the algorithm to detect thin smoke and separate fire smoke from other surface types. Moreover, the SSDA smoke distribution pattern exhibits a high spatial correlation with the global fire density map, suggesting that SSDA is capable of detecting smoke plumes of fires in near real-time across the globe.
5
Lu, Xiaoman, Xiaoyang Zhang, Fangjun Li, Mark A. Cochrane, and Pubu Ciren. "Detection of Fire Smoke Plumes Based on Aerosol Scattering Using VIIRS Data over Global Fire-Prone Regions." Remote Sensing 13, no. 2 (January 8, 2021): 196. http://dx.doi.org/10.3390/rs13020196.
Full textAbstract:
Smoke from fires significantly influences climate, weather, and human health. Fire smoke is traditionally detected using an aerosol index calculated from spectral contrast changes. However, such methods usually miss thin smoke plumes. It also remains challenging to accurately separate smoke plumes from dust, clouds, and bright surfaces. To improve smoke plume detections, this paper presents a new scattering-based smoke detection algorithm (SSDA) depending mainly on visible and infrared imaging radiometer suite (VIIRS) blue and green bands. The SSDA is established based on the theory of Mie scattering that occurs when the diameter of an atmospheric particulate is similar to the wavelength of the scattered light. Thus, smoke commonly causes Mie scattering in VIIRS blue and green bands because of the close correspondence between smoke particulate diameters and the blue/green band wavelengths. For developing the SSDA, training samples were selected from global fire-prone regions in North America, South America, Africa, Indonesia, Siberia, and Australia. The SSDA performance was evaluated against the VIIRS aerosol detection product and smoke detections from the ultraviolet aerosol index using manually labeled fire smoke plumes as a benchmark. Results show that the SSDA smoke detections are superior to existing products due chiefly to the improved ability of the algorithm to detect thin smoke and separate fire smoke from other surface types. Moreover, the SSDA smoke distribution pattern exhibits a high spatial correlation with the global fire density map, suggesting that SSDA is capable of detecting smoke plumes of fires in near real-time across the globe.
6
Lin, Ji, Haifeng Lin, and Fang Wang. "A Semi-Supervised Method for Real-Time Forest Fire Detection Algorithm Based on Adaptively Spatial Feature Fusion." Forests 14, no. 2 (February 11, 2023): 361. http://dx.doi.org/10.3390/f14020361.
Full textAbstract:
Forest fires occur frequently around the world, causing serious economic losses and human casualties. Deep learning techniques based on convolutional neural networks (CNN) are widely used in the intelligent detection of forest fires. However, CNN-based forest fire target detection models lack global modeling capabilities and cannot fully extract global and contextual information about forest fire targets. CNNs also pay insufficient attention to forest fires and are vulnerable to the interference of invalid features similar to forest fires, resulting in low accuracy of fire detection. In addition, CNN-based forest fire target detection models require a large number of labeled datasets. Manual annotation is often used to annotate the huge amount of forest fire datasets; however, this takes a lot of time. To address these problems, this paper proposes a forest fire detection model, TCA-YOLO, with YOLOv5 as the basic framework. Firstly, we combine the Transformer encoder with its powerful global modeling capability and self-attention mechanism with CNN as a feature extraction network to enhance the extraction of global information on forest fire targets. Secondly, in order to enhance the model’s focus on forest fire targets, we integrate the Coordinate Attention (CA) mechanism. CA not only acquires inter-channel information but also considers direction-related location information, which helps the model to better locate and identify forest fire targets. Integrated adaptively spatial feature fusion (ASFF) technology allows the model to automatically filter out useless information from other layers and efficiently fuse features to suppress the interference of complex backgrounds in the forest area for detection. Finally, semi-supervised learning is used to save a large amount of manual labeling effort. The experimental results show that the average accuracy of TCA-YOLO improves by 5.3 compared with the unimproved YOLOv5. TCA-YOLO also outperformed in detecting forest fire targets in different scenarios. The ability of TCA-YOLO to extract global information on forest fire targets was much improved. Additionally, it could locate forest fire targets more accurately. TCA-YOLO misses fewer forest fire targets and is less likely to be interfered with by forest fire-like targets. TCA-YOLO is also more focused on forest fire targets and better at small-target forest fire detection. FPS reaches 53.7, which means that the detection speed meets the requirements of real-time forest fire detection.
7
Johnston, Joshua, Lynn Johnston, Martin Wooster, Alison Brookes, Colin McFayden, and Alan Cantin. "Satellite Detection Limitations of Sub-Canopy Smouldering Wildfires in the North American Boreal Forest." Fire 1, no. 2 (August 10, 2018): 28. http://dx.doi.org/10.3390/fire1020028.
Full textAbstract:
We develop a simulation model for prediction of forest canopy interception of upwelling fire radiated energy from sub-canopy smouldering vegetation fires. We apply this model spatially across the North American boreal forest in order to map minimum detectable sub-canopy smouldering fire size for three satellite fire detection systems (sensor and algorithm), broadly representative of the Moderate Resolution Imaging Spectroradiometer (MODIS), Sea and Land Surface Temperature Radiometer (SLSTR) and Visible Infrared Imaging Radiometer Suite (VIIRS). We evaluate our results according to fire management requirements for “early detection” of wildland fires. In comparison to the historic fire archive (Canadian National Fire Database, 1980–2017), satellite data with a 1000 m pixel size used with an algorithm having a minimum MWIR channel BT elevation threshold of 5 and 3 K above background (e.g., MODIS or SLSTR) proves incapable of providing a sub-0.2 ha smouldering fire detection 70% and 45% of the time respectively, even assuming that the sensor overpassed the relevant location within the correct time window. By contrast, reducing the pixel area by an order of magnitude (e.g., 375 m pixels of VIIRS) and using a 3.5 K active fire detection threshold offers the potential for successfully detecting all fires when they are still below 0.2 ha. Our results represent a ‘theoretical best performance’ of remote sensing systems to detect sub-canopy smoldering fires early in their lifetime.
8
Ryu, Jinkyu, and Dongkurl Kwak. "Flame Detection Using Appearance-Based Pre-Processing and Convolutional Neural Network." Applied Sciences 11, no. 11 (May 31, 2021): 5138. http://dx.doi.org/10.3390/app11115138.
Full textAbstract:
It is important for fire detectors to operate quickly in the event of a fire, but existing conventional fire detectors sometimes do not work properly or there are problems where non-fire or false reporting occurs frequently. Therefore, in this study, HSV color conversion and Harris Corner Detection were used in the image pre-processing step to reduce the incidence of false detections. In addition, among the detected corners, the vicinity of the corner point facing the upper direction was extracted as a region of interest (ROI), and the fire was determined using a convolutional neural network (CNN). These methods were designed to detect the appearance of flames based on top-pointing properties, which resulted in higher accuracy and higher precision than when input images were still used in conventional object detection algorithms. This also reduced the false detection rate for non-fires, enabling high-precision fire detection.
9
Meidelfi, Dwiny, Hanriyawan Adnan Moodutor, Fanni Sukma, and Sandri Adnin. "Android Based Spark and Gas Leak Detection and Monitoring." Journal of Computer Networks, Architecture and High Performance Computing 4, no. 2 (July 21, 2022): 148–57. http://dx.doi.org/10.47709/cnahpc.v4i2.1489.
Full textAbstract:
LPG cylinder leakage is one of the causes of fires in the community. To prevent fires, a fire and gas leak detection and monitoring device were made using a fire detector sensor and an Android-based MQ-6 to trigger it. Data collection techniques in the manufacture of gas and fire leak detection using a flame detector and the MQ-6 sensor can be obtained from datasheets, journals, books and articles, and several internet sites that support the manufacture of this device. In the manufacture of gas leak detection devices or tools, there are also two parts, namely the first to make hardware (hardware), then software (software). The result of this tool detection is that users can find out the level of LPG due to leaking of LPG cylinders and detect fire using Android notifications in real-time and the data is displayed in detail on the browser page. The conclusion of this study is that users are safer because there is a gas leak, the tool will detect LPG gas, then a message will be displayed on the LCD screen and a notification on Android and the buzzer will automatically turn on. If there is a fire from detecting the gas leak, the fire detector will detect the fire, which will result in a notification sent to Android that there is a fire and the buzzer will turn on
10
Sun, Lijun. "Digital Print Synthesis Based on Image Processing and Interactive Technology." Journal of Physics: Conference Series 2146, no. 1 (January 1, 2022): 012028. http://dx.doi.org/10.1088/1742-6596/2146/1/012028.
Full textAbstract:
Abstract Fire is a common disaster, which causes major threats and losses to human life and property. Countries around the world have been committed to the study of the mechanism and internal mechanism of fires, with the goal of preventing fires from occurring and minimizing the losses caused by fires. Among the many methods, fire detection technology is an effective method to prevent and reduce the occurrence of fire. This article focuses on the research of the fire detection system based on artificial intelligence technology, improves the accuracy of the fire detection system by introducing artificial intelligence technology into the fire detection system, and uses experiments to verify the error rate of the artificial intelligence technology fire detection system. The experimental results show that the system’s detection of fire is not very different from the actual situation, and the error rate is within 10%. Then compared with the traditional detection system, the detection performance is relatively high, and the error rate can be reduced by one time.
11
Huang, Jingwen, Jiashun Zhou, Huizhou Yang, Yunfei Liu, and Han Liu. "A Small-Target Forest Fire Smoke Detection Model Based on Deformable Transformer for End-to-End Object Detection." Forests 14, no. 1 (January 16, 2023): 162. http://dx.doi.org/10.3390/f14010162.
Full textAbstract:
Forest fires have continually endangered personal safety and social property. To reduce the occurrences of forest fires, it is essential to detect forest fire smoke accurately and quickly. Traditional forest fire smoke detection based on convolutional neural networks (CNNs) needs many hand-designed components and shows poor ability to detect small and inconspicuous smoke in complex forest scenes. Therefore, we propose an improved early forest fire smoke detection model based on deformable transformer for end-to-end object detection (deformable DETR). We use deformable DETR as a baseline containing the best sparse spatial sampling for smoke with deformable convolution and relation modeling capability of the transformer. We integrate a Multi-scale Context Contrasted Local Feature module (MCCL) and a Dense Pyramid Pooling module (DPPM) into the feature extraction module for perceiving features of small or inconspicuous smoke. To improve detection accuracy and reduce false and missed detections, we propose an iterative bounding box combination method to generate precise bounding boxes which can cover the entire smoke object. In addition, we evaluate the proposed approach using a quantitative and qualitative self-made forest fire smoke dataset, which includes forest fire smoke images of different scales. Extensive experiments show that our improved model’s forest fire smoke detection accuracy is significantly higher than that of the mainstream models. Compared with deformable DETR, our model shows better performance with improvement of mAP (mean average precision) by 4.2%, APS (AP for small objects) by 5.1%, and other metrics by 2% to 3%. Our model is adequate for early forest fire smoke detection with high detection accuracy of different-scale smoke objects.
12
Abdusalomov, Akmalbek, Nodirbek Baratov, Alpamis Kutlimuratov, and Taeg Keun Whangbo. "An Improvement of the Fire Detection and Classification Method Using YOLOv3 for Surveillance Systems." Sensors 21, no. 19 (September 29, 2021): 6519. http://dx.doi.org/10.3390/s21196519.
Full textAbstract:
Currently, sensor-based systems for fire detection are widely used worldwide. Further research has shown that camera-based fire detection systems achieve much better results than sensor-based methods. In this study, we present a method for real-time high-speed fire detection using deep learning. A new special convolutional neural network was developed to detect fire regions using the existing YOLOv3 algorithm. Due to the fact that our real-time fire detector cameras were built on a Banana Pi M3 board, we adapted the YOLOv3 network to the board level. Firstly, we tested the latest versions of YOLO algorithms to select the appropriate algorithm and used it in our study for fire detection. The default versions of the YOLO approach have very low accuracy after training and testing in fire detection cases. We selected the YOLOv3 network to improve and use it for the successful detection and warning of fire disasters. By modifying the algorithm, we recorded the results of a rapid and high-precision detection of fire, during both day and night, irrespective of the shape and size. Another advantage is that the algorithm is capable of detecting fires that are 1 m long and 0.3 m wide at a distance of 50 m. Experimental results showed that the proposed method successfully detected fire candidate areas and achieved a seamless classification performance compared to other conventional fire detection frameworks.
13
Xue, Qilin, Haifeng Lin, and Fang Wang. "FCDM: An Improved Forest Fire Classification and Detection Model Based on YOLOv5." Forests 13, no. 12 (December 12, 2022): 2129. http://dx.doi.org/10.3390/f13122129.
Full textAbstract:
Intense, large-scale forest fires are damaging and very challenging to control. Locations, where various types of fire behavior occur, vary depending on environmental factors. According to the burning site of forest fires and the degree of damage, this paper considers the classification and identification of surface fires and canopy fires. Deep learning-based forest fire detection uses convolutional neural networks to automatically extract multidimensional features of forest fire images with high detection accuracy. To accurately identify different forest fire types in complex backgrounds, an improved forest fire classification and detection model (FCDM) based on YOLOv5 is presented in this paper, which uses image-based data. By changing the YOLOv5 bounding box loss function to SIoU Loss and introducing directionality in the cost of the loss function to achieve faster convergence, the training and inference of the detection algorithm are greatly improved. The Convolutional Block Attention Module (CBAM) is introduced in the network to fuse channel attention and spatial attention to improve the classification recognition accuracy. The Path Aggregation Network (PANet) layer in the YOLOv5 algorithm is improved into a weighted Bi-directional Feature Pyramid Network (BiFPN) to fuse and filter forest fire features of different dimensions to improve the detection of different types of forest fires. The experimental results show that this improved forest fire classification and identification model outperforms the YOLOv5 algorithm in both detection performances. The mAP@0.5 of fire detection, surface fire detection, and canopy fire detection was improved by 3.9%, 4.0%, and 3.8%, respectively. Among them, the mAP@0.5 of surface fire reached 83.1%, and the canopy fire detection reached 90.6%. This indicates that the performance of our proposed improved model has been effectively improved and has some application prospects in forest fire classification and recognition.
14
Jadhav, Kartik, Ganesh Gaikwad, Shubham Wagh, Adesh Navthar, and Prof Suryawanshi A. S. "Efficient Deep CNN-Based Fire Detection and Localization in Machine Learning Video Surveillance Applications." International Journal for Research in Applied Science and Engineering Technology 10, no. 11 (November 30, 2022): 388–94. http://dx.doi.org/10.22214/ijraset.2022.47333.
Full textAbstract:
Abstract: Early warning is important to reduce loss of life and various industries due to fire. Accidents caused by undetected fires cost the world a lot of money. The demand for effective fire alarm systems is growing. Existing fire and smoke detectors fail due to system inefficiency. Analysis of live camera data enables real-time fire detection. The properties of the fire flame are examined and the fire is recognized using edge detection and thresholding methods, resulting in a fire detected model. Detects dangerous fires identified based on size, speed, volume and structure. In this paper, we propose an emerging fire detection system based on a convolutional neural network. Experimental results of the model on our dataset show that it has good fire detection ability and real-time multi-level fire detection ability.
15
Abdusalomov, Akmalbek Bobomirzaevich, Mukhriddin Mukhiddinov, Alpamis Kutlimuratov, and Taeg Keun Whangbo. "Improved Real-Time Fire Warning System Based on Advanced Technologies for Visually Impaired People." Sensors 22, no. 19 (September 26, 2022): 7305. http://dx.doi.org/10.3390/s22197305.
Full textAbstract:
Early fire detection and notification techniques provide fire prevention and safety information to blind and visually impaired (BVI) people within a short period of time in emergency situations when fires occur in indoor environments. Given its direct impact on human safety and the environment, fire detection is a difficult but crucial problem. To prevent injuries and property damage, advanced technology requires appropriate methods for detecting fires as quickly as possible. In this study, to reduce the loss of human lives and property damage, we introduce the development of the vision-based early flame recognition and notification approach using artificial intelligence for assisting BVI people. The proposed fire alarm control system for indoor buildings can provide accurate information on fire scenes. In our proposed method, all the processes performed manually were automated, and the performance efficiency and quality of fire classification were improved. To perform real-time monitoring and enhance the detection accuracy of indoor fire disasters, the proposed system uses the YOLOv5m model, which is an updated version of the traditional YOLOv5. The experimental results show that the proposed system successfully detected and notified the occurrence of catastrophic fires with high speed and accuracy at any time of day or night, regardless of the shape or size of the fire. Finally, we compared the competitiveness level of our method with that of other conventional fire-detection methods to confirm the seamless classification results achieved using performance evaluation matrices.
16
Schultze, Thorsten, Thorsten Kempka, and Ingolf Willms. "Audio–video fire-detection of open fires." Fire Safety Journal 41, no. 4 (June 2006): 311–14. http://dx.doi.org/10.1016/j.firesaf.2006.01.002.
Full text
17
Lin, Ji, Haifeng Lin, and Fang Wang. "STPM_SAHI: A Small-Target Forest Fire Detection Model Based on Swin Transformer and Slicing Aided Hyper Inference." Forests 13, no. 10 (September 30, 2022): 1603. http://dx.doi.org/10.3390/f13101603.
Full textAbstract:
Forest fires seriously destroy the world’s forest resources and endanger biodiversity. The traditional forest fire target detection models based on convolutional neural networks (CNNs) lack the ability to deal with the relationship between visual elements and objects. They also have low detection accuracy for small-target forest fires. Therefore, this paper proposes an improved small-target forest fire detection model, STPM_SAHI. We use the latest technology in the field of computer vision, the Swin Transformer backbone network, to extract the features of forest fires. Its self-attention mechanism can capture the global information of forest fires to obtain larger receptive fields and contextual information. We integrated the Swin Transformer backbone network into the Mask R-CNN detection framework, and PAFPN was used to replace the original FPN as the feature fusion network, which can reduce the propagation path of the main feature layer and eliminate the impact of down-sampling fusion. After the improved model was trained, the average precision (AP0.5) of forest fire target detection at different scales reached 89.4. Then, Slicing Aided Hyper Inference technology was integrated into the improved forest fire detection model, which solved the problem that small-target forest fires pixels only account for a small proportion and lack sufficient details, which are difficult to be detected by the traditional target detection models. The detection accuracy of small-target forest fires was significantly improved. The average precision (AP0.5) increased by 8.1. Through an ablation experiment, we have proved the effectiveness of each module of the improved forest fire detection model. Furthermore, the forest fire detection accuracy is significantly better than that of the mainstream models. Our model can also detect forest fire targets with very small pixels. Our model is very suitable for small-target forest fire detection. The detection accuracy of forest fire targets at different scales is also very high and meets the needs of real-time forest fire detection.
18
Kumar, Aman, and Flavia D Gonsalves. "Computer Vision Based Fire Detection System Using OpenCV - A Case Study." Research & Review: Machine Learning and Cloud Computing 1, no. 2 (June 23, 2022): 25–33. http://dx.doi.org/10.46610/rrmlcc.2022.v01i02.005.
Full textAbstract:
Conventional fire detection system was based mechanical sensor for fire detection. The smoke particles in the surrounding detected by sensors in the traditional fire detection system. However, this can also lead to false alarms. For example, a person smoking in a room of can activate a general fire alarm system. In addition, these systems are expensive and ineffective if the fire is far away from the detector. An alternatives fire detection system such as system based on computer vision and Image/video Processing technology to manage false alarms from conventional fire detection. One of the most cost-effective ways is to use surveillance cameras to detect fires and alert affected parties. In the following proposed system proposes a technique which will be monitor the outburst of a fire anywhere within the camera range using a surveillance camera. In this Paper, fire alarm system will be developed to efficiently detect fires and protect lives and property from fire hazards. This research describes a fire detection system that uses color and motion models derived from video sequences. The proposed approach identifies color changes and mobility in common areas to identify fires and can therefore be used both in real time and in datasets.
19
Higa, Leandro, José Marcato Junior, Thiago Rodrigues, Pedro Zamboni, Rodrigo Silva, Laisa Almeida, Veraldo Liesenberg, et al. "Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery." Remote Sensing 14, no. 3 (January 31, 2022): 688. http://dx.doi.org/10.3390/rs14030688.
Full textAbstract:
Fire in Brazilian Pantanal represents a serious threat to biodiversity. The Brazilian National Institute of Spatial Research (INPE) has a program named Queimadas, which estimated from January 2020 to October 2020, a burned area in Pantanal of approximately 40,606 km2. This program also provides daily data of active fire (fires spots) from a methodology that uses MODIS (Aqua and Terra) sensor data as reference satellites, which presents limitations mainly when dealing with small active fires. Remote sensing researches on active fire dynamics have contributed to wildfire comprehension, despite generally applying low spatial resolution data. Convolutional Neural Networks (CNN) associated with high- and medium-resolution remote sensing data may provide a complementary strategy to small active fire detection. We propose an approach based on object detection methods to map active fire in the Pantanal. In this approach, a post-processing strategy is adopted based on Non-Max Suppression (NMS) to reduce the number of highly overlapped detections. Extensive experiments were conducted, generating 150 models, as five-folds were considered. We generate a public dataset with 775-RGB image patches from the Wide Field Imager (WFI) sensor onboard the China Brazil Earth Resources Satellite (CBERS) 4A. The patches resulted from 49 images acquired from May to August 2020 and present a spatial and temporal resolutions of 55 m and five days, respectively. The proposed approach uses a point (active fire) to generate squared bounding boxes. Our findings indicate that accurate results were achieved, even considering recent images from 2021, showing the generalization capability of our models to complement other researches and wildfire databases such as the current program Queimadas in detecting active fire in this complex environment. The approach may be extended and evaluated in other environmental conditions worldwide where active fire detection is still a required information in fire fighting and rescue initiatives.
20
SIRIN, A. A., M. A. MEDVEDEVA, V. YU ITKIN, D. A. MAKAROV, and V. N. KOROTKOV. "PEAT FIRE DETECTION TO ESTIMATE GREENHOUSE GAS EMISSIONS." Meteorologiya i Gidrologiya, no. 10 (October 2022): 33–45. http://dx.doi.org/10.52002/0130-2906-2022-10-33-45.
Full textAbstract:
Peat fires differ from other wildfires by significant carbon loss, the emission of greenhouse gases and other combustion products as well as by serious environmental consequences. Not only biomass but also peat is burnt. A possibility of detecting peat fires from satellite and ground-based data is considered for the fires in the Moscow region in 2010. The peat fire detection technique was tested by superimposing data on thermal anomalies from Terra/Aqua MODIS satellite data on the peatland contours, as well as by analyzing the vegetation cover changes before fires and the next year using the Landsat satellite multispectral data. Threshold values were found for the fire duration, maximum temperature, and maximum fire radiative power that characterize peat fires and can be used to discriminate between fires on peat lands and peat fires themselves for taking into account emissions not only from biomass burning but also from soil carbon loss.
21
Pan, Jin, Xiaoming Ou, and Liang Xu. "A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN." Forests 12, no. 6 (June 10, 2021): 768. http://dx.doi.org/10.3390/f12060768.
Full textAbstract:
Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.
22
Xue, Zhenyang, Haifeng Lin, and Fang Wang. "A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement." Forests 13, no. 8 (August 20, 2022): 1332. http://dx.doi.org/10.3390/f13081332.
Full textAbstract:
Forest fires are highly unpredictable and extremely destructive. Traditional methods of manual inspection, sensor-based detection, satellite remote sensing and computer vision detection all have their obvious limitations. Deep learning techniques can learn and adaptively extract features of forest fires. However, the small size of the forest fire target in the long-range-captured forest fire images causes the model to fail to learn effective information. To solve this problem, we propose an improved forest fire small-target detection model based on YOLOv5. This model requires cameras as sensors for detecting forest fires in practical applications. First, we improved the Backbone layer of YOLOv5 and adjust the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 to the Spatial Pyramid Pooling-Fast-Plus (SPPFP) module for a better focus on the global information of small forest fire targets. Then, we added the Convolutional Block Attention Module (CBAM) attention module to improve the identifiability of small forest fire targets. Second, the Neck layer of YOLOv5 was improved by adding a very-small-target detection layer and adjusting the Path Aggregation Network (PANet) to the Bi-directional Feature Pyramid Network (BiFPN). Finally, since the initial small-target forest fire dataset is a small sample dataset, a migration learning strategy was used for training. Experimental results on an initial small-target forest fire dataset produced by us show that the improved structure in this paper improves mAP@0.5 by 10.1%. This demonstrates that the performance of our proposed model has been effectively improved and has some application prospects.
23
Shin, Young Min, You Ri Lim, Bong Jun Kim, Hwang Jin Kim, Dong Hun Han, and Chang Seop Lee. "Effectiveness Analysis of Unwanted Fire Alarm Using Carbon Monoxide Sensors." Fire Science and Engineering 36, no. 5 (October 31, 2022): 40–50. http://dx.doi.org/10.7731/kifse.56c9f690.
Full textAbstract:
A carbon monoxide sensor was applied with smoke detectors, which trigger unwanted fire alarms, to improve detection reliability. Standardized fire and unwanted fire tests according to UL 268 and scenario-based tests for unwanted fire alarms were performed to analyze the detection effectiveness in fire and unwanted fire situations. Studies on improving unwanted fire alarms using carbon monoxide sensors have been conducted in various fields. However, additional concentration measurements using carbon monoxide sensors in various fire and unwanted fire conditions should be performed for institutional approval of detection effectiveness. Further research is required to determine the carbon monoxide concentration that can clearly distinguish unwanted fires from actual fires.
24
Kalmykov, S. P., and V. M. Esin. "Fire detection time." Пожаровзрывобезопасность 26, no. 11 (November 2017): 52–63. http://dx.doi.org/10.18322/pvb.2017.26.11.52-63.
Full text
25
Hoefer, Ulrich, and Daniel Gutmachera. "Fire Gas Detection." Procedia Engineering 47 (2012): 1446–59. http://dx.doi.org/10.1016/j.proeng.2012.09.430.
Full text
26
Kushnir, A., and B. Kopchak. "DEVELOPMENT OF COMPUTER VISION-BASED AUTOMATIC FLAME DETECTION ALGORITHM USING MATLAB SOFTWARE ENVIRONMENT." Fire Safety 36 (July 20, 2020): 49–58. http://dx.doi.org/10.32447/20786662.36.2020.05.
Full textAbstract:
Introduction. Fire detection systems plays an important role in protecting objects from fires and saving lives. In traditional fire detection systems, fire detectors detect fires by combustion of by-products, such as smoke, temperature, flame radiation. This principle is effective, but unfortunately, the fire detector works with a significant delay if the ignition source is not in close proximity to it. In addition, such systems have a high frequency of false positives. The most promising area for early fire detection is the use of computer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systemscomputer vision based fire detection systems, as they detect fires rather than their combustion products. Such systems, as well as traditional fire detection systems, analyze the signs of a fire, such as smoke, flames, and even the air temperature by means of the image coming directly from the cameras, due to which the range of the system increases significantly. Unlike traditional systems, they are more efficient, do not require indoor spaces, have high performance and minimize the number of false positives. In addition, when notifying the operator about a fire, the video system can provide him with an image of probable ignition place.Fire detection algorithms are quite complex because the signs of a fire are non-static. Today, more and more scientists are trying to develop algorithms and methods that will detect fires at an early stage in the video stream with high accuracy, without false positives. When creating such algorithms, there are four main approaches. These are flame colour segmentation, motion de-tection in the image, analysis of spatial changes in brightness and analysis of temporal changes in boundaries. Each approach requires the development of its own individual algorithm, combining them, which is quite a difficult task. However, all algorithms are based on the process of selecting colours in the image that are characteristic of fire. There are many algorithms that use two or three approaches and they provide good results. Using the MATLAB software environment and its standard packages to create a flame detection system is considered in this paper.Purpose. The research aims to develop an algorithm for automatic flame detection in images based on pixel analysis, which identifies the colour of the flame and flame area using the MATLAB software environment, in order to further create a reliable computer vision-based flame detection system.Results. The MATLAB software environment includes Image Acquisition Toolbox and Image Processing Toolbox, which are compatible environments for developing real-time imaging applications that can come from digital video cameras, satellite and aviation on-board sensors, and other scientific devices. Using them, one can implement new ideas, including the development of fire detection algorithms.The flame has a fairly uniform intensity compared to other intensities of objects, unlike smoke. That's why there are so many flame-based fire detection algorithms. However, in practice, developing an effective algorithm is not an easy task, because the image under study may contain objects that have signs of flame. In the image, you need to select the pixels with the characteristic colour that are inherent in the flame. At this stage, various images with flames in the RGB colour model were analyzed and the mean value of their intensity and standard deviation (R, G and B) were determined. Image segmentation was performed on the basis of the obtained values. The purpose of segmentation was to highlight the flame in the image. However, there may be other objects in the image whose pixel intensities match the flame pixel intensities. As a result, in addition to the flame, other objects may be highlighted in the segmented image. Based on the previously selected segmentation method, we can assume that the flame in this image occupies the largest area. Therefore, another criterion was chosen for the flame search, based on the area, which enabled to remove other objects that do not belong to the flame. In the final stage, the flame in the image is highlighted by a rectangle.Conclusions. The possibility of using the MATLAB software environment with the Image Acquisition Toolbox and Image Processing Toolbox packages to create a computer vision based flame detection system is considered. The functions of the packages allow you to implement new ideas when creating algorithms for automatic fire detection. The article develops the algorithm for automatic flame detection in the image based on the analysis of flame colour pixels and flame area. Various images with flames in the RGB colour model were analyzed and their mean value and standard deviation were determined. Image segmentation was performed on the basis of the obtained values. Experimental studies in the MATLAB software environment have proved the effi-ciency of the developed algorithm. To create a reliable computer vision based flame detection system in future, it is proposed to develop an algorithm that would analyze the boundaries, shape and flicker of the flame in addition to analyzing the flame colour pixels and flame area.
27
Yuan, Chi, Youmin Zhang, and Zhixiang Liu. "A survey on technologies for automatic forest fire monitoring, detection, and fighting using unmanned aerial vehicles and remote sensing techniques." Canadian Journal of Forest Research 45, no. 7 (July 2015): 783–92. http://dx.doi.org/10.1139/cjfr-2014-0347.
Full textAbstract:
Because of their rapid maneuverability, extended operational range, and improved personnel safety, unmanned aerial vehicles (UAVs) with vision-based systems have great potential for monitoring, detecting, and fighting forest fires. Over the last decade, UAV-based forest fire fighting technology has shown increasing promise. This paper presents a systematic overview of current progress in this field. First, a brief review of the development and system architecture of UAV systems for forest fire monitoring, detection, and fighting is provided. Next, technologies related to UAV forest fire monitoring, detection, and fighting are briefly reviewed, including those associated with fire detection, diagnosis, and prognosis, image vibration elimination, and cooperative control of UAVs. The final section outlines existing challenges and potential solutions in the application of UAVs to forest firefighting.
28
Al Rakib, Md Abdullah, Md Moklesur Rahman, Md Shamsul Alam Anik, Fayez Ahmed Jahangir Masud, Md Ashiqur Rahman, Md Saddam Hossain, and Fysol Ibna Abbas. "Fire Detection and Water Discharge Activity for Fire Fighting Robots using IoT." European Journal of Engineering and Technology Research 7, no. 2 (April 13, 2022): 128–33. http://dx.doi.org/10.24018/ejeng.2022.7.2.2742.
Full textAbstract:
A fire is a calamity that can result in the loss of life, property damage, and the victim's lasting incapacity. Our obstacle remover and fireman Robot has been declared. In the case of a fire, we are compelled to employ human resources, which are not safe, to rescue people and put out the fire. With the advent of technology, particularly in robotics, it is now possible to respond quickly to fire locations and combat fires. This would increase firefighter efficiency while simultaneously preventing them from putting their lives in danger. In this project, we created a prototype robot using Arduino that detects and extinguishes fires autonomously. When the flame sensor detects a fire, the water pump and servo motor are activated. The capacity to detect fire sites automatically and extinguish fire remotely at a distance of 20 cm from the fire. The robot is designed to locate fires and spray water into them in order to decrease the amount of damage.
29
Yadav, Amit, Abhijeet Agawal, Pramod Kumar, and Tejaswi Sachwani. "DESIGN AND ANALYSIS OF AN INTELLIGENT FIRE DETECTION SYSTEM FOR AIRCRAFT." International Journal of Engineering Technologies and Management Research 5, no. 2 (May 4, 2020): 260–73. http://dx.doi.org/10.29121/ijetmr.v5.i2.2018.656.
Full textAbstract:
Fire detection system and fire warning are design features of an aircraft. Fire detection system protects the aircraft and passengers both in case of actual fire during flight. But spurious fire warning during flight creates a panic situation in flight crews and passengers. The conventional fire alarm system of an aircraft is triggered by false signal. ANN based fire detection system provides real observation of deployed zones. An intelligent fire detection system is developed based on artificial neural network using three detection information such as heat (temperature), smoke density and CO gas. This Information helps in determining the probability of three representative of Fire condition which is Fire, smoke and no fire. The simulated MATLAB results Show that the errors in identification are very less. The neural network based fire detection system integrates different types of sensor data and improves the ability of system to correct prediction of fires. It gives early alarm when any kind of fire broke out and helps to decrease in spurious warning.
30
Zheng, Xin, Feng Chen, Liming Lou, Pengle Cheng, and Ying Huang. "Real-Time Detection of Full-Scale Forest Fire Smoke Based on Deep Convolution Neural Network." Remote Sensing 14, no. 3 (January 23, 2022): 536. http://dx.doi.org/10.3390/rs14030536.
Full textAbstract:
To reduce the loss induced by forest fires, it is very important to detect the forest fire smoke in real time so that early and timely warning can be issued. Machine vision and image processing technology is widely used for detecting forest fire smoke. However, most of the traditional image detection algorithms require manual extraction of image features and, thus, are not real-time. This paper evaluates the effectiveness of using the deep convolutional neural network to detect forest fire smoke in real time. Several target detection deep convolutional neural network algorithms evaluated include the EfficientDet (EfficientDet: Scalable and Efficient Object Detection), Faster R-CNN (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks), YOLOv3 (You Only Look Once V3), and SSD (Single Shot MultiBox Detector) advanced CNN (Convolutional Neural Networks) model. The YOLOv3 showed a detection speed up to 27 FPS, indicating it is a real-time smoke detector. By comparing these algorithms with the current existing forest fire smoke detection algorithms, it can be found that the deep convolutional neural network algorithms result in better smoke detection accuracy. In particular, the EfficientDet algorithm achieves an average detection accuracy of 95.7%, which is the best real-time forest fire smoke detection among the evaluated algorithms.
31
Kumar, S. Senthil, and Ms D. Nivya. "Credit Card Fraud Detection using Fire Fly Algorithm." International Journal of Trend in Scientific Research and Development Volume-1, Issue-6 (October 31, 2017): 728–32. http://dx.doi.org/10.31142/ijtsrd4672.
Full text
32
Shvaiko, Valerii, Olena Bandurka, Vadym Shpuryk, and Yevhen V. Havrylko. "METHODS FOR DETECTING FIRES IN ECOSYSTEMS USING LOW-RESOLUTION SPACE IMAGES." Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska 11, no. 1 (March 31, 2021): 15–19. http://dx.doi.org/10.35784/iapgos.2576.
Full textAbstract:
The paper presents the methods for fire identification using low-resolution space images obtained from Terra Modis and NOAA satellites. There are lots of algorithms to identify potentially "fire pixels" (PF). They are based on the assessment of temperature in spectral ranges from 3.5–4 to 10.5–11.5 microns. One of the problematic aspects in the Fire Detection Method using low-resolution space images is "Cloud and Water Masking". To identify "fire pixels", it is important to exclude from the analysis fragments of images that are covered with clouds and occupied by water objects. Identification of pixels in which one or more fires are actively burning at the time of passing over the Earth is the basis of the algorithm for detecting potentially "fire pixels". The algorithm requires a significant increase in radiation in the range of 4 micrometers, as well as on the observed radiation in the range of 11 micrometers. The algorithm investigates each pixel in a scene that is assigned one of the following classes as a result: lack of data, cloud, water, potentially fire or uncertain. The pixels that lack actual data are immediately classified as "missing data (NULL)" and excluded from further consideration. Cloud and water pixels, defined by the cloud masking technique and water objects, belong to cloud and water classes, respectively. The fire detection algorithm investigates only those pixels of the Earth's surface that are classified as potentially fire or uncertain. The method was implemented using the Visual Programming Tool PowerBuilder in the data processing system of Erdas Imaging. As a result of the use of the identification method, fires in the Chornobyl exclusion zone, steppe fires and fires at gas wells were detected. Using the method of satellite fire identification is essential for the prompt detection of fires for remote forests or steppes that are poorly controlled by ground monitoring methods.
33
Seydi, Seyd Teymoor, Vahideh Saeidi, Bahareh Kalantar, Naonori Ueda, and Alfian Abdul Halin. "Fire-Net: A Deep Learning Framework for Active Forest Fire Detection." Journal of Sensors 2022 (February 21, 2022): 1–14. http://dx.doi.org/10.1155/2022/8044390.
Full textAbstract:
Forest conservation is crucial for the maintenance of a healthy and thriving ecosystem. The field of remote sensing (RS) has been integral with the wide adoption of computer vision and sensor technologies for forest land observation. One critical area of interest is the detection of active forest fires. A forest fire, which occurs naturally or manually induced, can quickly sweep through vast amounts of land, leaving behind unfathomable damage and loss of lives. Automatic detection of active forest fires (and burning biomass) is hence an important area to pursue to avoid unwanted catastrophes. Early fire detection can also be useful for decision makers to plan mitigation strategies as well as extinguishing efforts. In this paper, we present a deep learning framework called Fire-Net, that is trained on Landsat-8 imagery for the detection of active fires and burning biomass. Specifically, we fuse the optical (Red, Green, and Blue) and thermal modalities from the images for a more effective representation. In addition, our network leverages the residual convolution and separable convolution blocks, enabling deeper features from coarse datasets to be extracted. Experimental results show an overall accuracy of 97.35%, while also being able to robustly detect small active fires. The imagery for this study is taken from Australian and North American forests regions, the Amazon rainforest, Central Africa and Chernobyl (Ukraine), where forest fires are actively reported.
34
Swarajya Lakshmi, B. "Fire Detection Using Image Processing." Asian Journal of Computer Science and Technology 10, no. 2 (November 5, 2021): 14–19. http://dx.doi.org/10.51983/ajcst-2021.10.2.2883.
Full textAbstract:
Fire disasters have always been a threat to homes and businesses even with the various systems in place to prevent them. They cause property damage, injuries and even death. Preparedness is vital when dealing with fires. They spread uncontrollably and are difficult to contain. To contain them it is necessary for the fire to be detected early. Image fire detection heavily relies on an algorithmic analysis of images. However, the accuracy is lower, the detection is delayed and in common detection algorithms a large number of computation, including the image features being extracted manually and using machine. Therefore, in this paper, novel image detection which will be based on the advanced object detection like CNN model of YOLO v3 is proposed. The average precision of the algorithm based on YOLO v3 reaches to 81.76% and also it has the stronger robustness of detection performance, thereby satisfying the requirements of the real-time detection.
35
Marsha, Amy L., and Narasimhan K. Larkin. "Evaluating Satellite Fire Detection Products and an Ensemble Approach for Estimating Burned Area in the United States." Fire 5, no. 5 (September 22, 2022): 147. http://dx.doi.org/10.3390/fire5050147.
Full textAbstract:
Fire location and burning area are essential parameters for estimating fire emissions. However, ground-based fire data (such as fire perimeters from incident reports) are often not available with the timeliness required for real-time forecasting. Fire detection products derived from satellite instruments such as the GOES-16 Advanced Baseline Imager or MODIS, on the other hand, are available in near real-time. Using a ground fire dataset of 2699 fires during 2017–2019, we fit a series of linear models that use multiple satellite fire detection products (HMS aggregate fire product, GOES-16, MODIS, and VIIRS) to assess the ability of satellite data to detect and estimate total burned area. It was found that on average models fit with fire detections from GOES-16 products performed better than those developed from other satellites in the study (modelled R2 = 0.84 and predictive R2 = 0.88). However, no single satellite product was found to best estimate incident burned area, highlighting the need for an ensemble approach. With our proposed modelling ensemble, we demonstrate its ability to estimate burned area and suggest its further use in daily fire tracking and emissions-modeling frameworks.
36
Chen, Gong, Hang Zhou, Zhongyuan Li, Yucheng Gao, Di Bai, Renjie Xu, and Haifeng Lin. "Multi-Scale Forest Fire Recognition Model Based on Improved YOLOv5s." Forests 14, no. 2 (February 6, 2023): 315. http://dx.doi.org/10.3390/f14020315.
Full textAbstract:
The frequent occurrence of forest fires causes irreparable damage to the environment and the economy. Therefore, the accurate detection of forest fires is particularly important. Due to the various shapes and textures of flames and the large variation in the target scales, traditional forest fire detection methods have high false alarm rates and poor adaptability, which results in severe limitations. To address the problem of the low detection accuracy caused by the multi-scale characteristics and changeable morphology of forest fires, this paper proposes YOLOv5s-CCAB, an improved multi-scale forest fire detection model based on YOLOv5s. Firstly, coordinate attention (CA) was added to YOLOv5s in order to adjust the network to focus more on the forest fire features. Secondly, Contextual Transformer (CoT) was introduced into the backbone network, and a CoT3 module was built to reduce the number of parameters while improving the detection of forest fires and the ability to capture global dependencies in forest fire images. Then, changes were made to Complete-Intersection-Over-Union (CIoU) Loss function to improve the network’s detection accuracy for forest fire targets. Finally, the Bi-directional Feature Pyramid Network (BiFPN) was constructed at the neck to provide the model with a more effective fusion capability for the extracted forest fire features. The experimental results based on the constructed multi-scale forest fire dataset show that YOLOv5s-CCAB increases AP@0.5 by 6.2% to 87.7%, and the FPS reaches 36.6. This indicates that YOLOv5s-CCAB has a high detection accuracy and speed. The method can provide a reference for the real-time, accurate detection of multi-scale forest fires.
37
Zaini, Zaini, and Taffany Hudalil Alvy. "Design of Monitoring System for Hazardous Gas and Fire Detection In Building Based On Internet of Things." Andalas Journal of Electrical and Electronic Engineering Technology 2, no. 1 (June 24, 2022): 13–20. http://dx.doi.org/10.25077/ajeeet.v2i1.20.
Full textAbstract:
Fires and gas leaks are events that still occur frequently. This incident is usually caused by various factors including leakage of LPG gas cylinders, cigarette butts that are disposed of carelessly, short circuits of electric current and so on. Generally, fires and gas leaks can only be detected if the fire has already grown or a lot of smoke comes out of the building. Therefore, a monitoring system for detecting dangerous gases and fires in buildings based on the Internet of Things was created that can monitor the condition of the building through a website as well as send notifications to the Telegram application on smartphones. The detection system implemented uses a flame sensor as a fire detector, an MQ-2 gas sensor as a detector of hazardous gases (CO, CO2, and CH4), and NodeMCU as a module to transmit data. The system will work continuously in real time, if gas is detected that exceeds the threshold or a fire is detected, the system will send a notification to Telegram and the website will display the value and status of the sensor and a map of the area where the fire or gas leak occurred. The results of the detection system created to be able to provide solutions so that cases of fire and gas leaks can be handled early by detecting signs of fire or gas leaks and sending the information to users via the website and notifications.
38
Jagatheesaperumal, Senthil Kumar, Khan Muhammad, Abdul Khader Jilani Saudagar, and Joel J. P. C. Rodrigues. "Automated Fire Extinguishing System Using a Deep Learning Based Framework." Mathematics 11, no. 3 (January 26, 2023): 608. http://dx.doi.org/10.3390/math11030608.
Full textAbstract:
Fire accidents occur in every part of the world and cause a large number of casualties because of the risks involved in manually extinguishing the fire. In most cases, humans cannot detect and extinguish fire manually. Fire extinguishing robots with sophisticated functionalities are being rapidly developed nowadays, and most of these systems use fire sensors and detectors. However, they lack mechanisms for the early detection of fire, in case of casualties. To detect and prevent such fire accidents in its early stages, a deep learning-based automatic fire extinguishing mechanism was introduced in this work. Fire detection and human presence in fire locations were carried out using convolution neural networks (CNNs), configured to operate on the chosen fire dataset. For fire detection, a custom learning network was formed by tweaking the layer parameters of CNN for detecting fires with better accuracy. For human detection, Alex-net architecture was employed to detect the presence of humans in the fire accident zone. We experimented and analyzed the proposed model using various optimizers, activation functions, and learning rates, based on the accuracy and loss metrics generated for the chosen fire dataset. The best combination of neural network parameters was evaluated from the model configured with an Adam optimizer and softmax activation, driven with a learning rate of 0.001, providing better accuracy for the learning model. Finally, the experiments were tested using a mobile robotic system by configuring them in automatic and wireless control modes. In automatic mode, the robot was made to patrol around and monitor for fire casualties and fire accidents. It automatically extinguished the fire using the learned features triggered through the developed model.
39
Namburu, Anupama, Prabha Selvaraj, Senthilkumar Mohan, Sumathi Ragavanantham, and Elsayed Tag Eldin. "Forest Fire Identification in UAV Imagery Using X-MobileNet." Electronics 12, no. 3 (February 1, 2023): 733. http://dx.doi.org/10.3390/electronics12030733.
Full textAbstract:
Forest fires are caused naturally by lightning, high atmospheric temperatures, and dryness. Forest fires have ramifications for both climatic conditions and anthropogenic ecosystems. According to various research studies, there has been a noticeable increase in the frequency of forest fires in India. Between 1 January and 31 March 2022, the country had 136,604 fire points. They activated an alerting system that indicates the location of a forest fire detected using MODIS sensor data from NASA Aqua and Terra satellite images. However, the satellite passes the country only twice and sends the information to the state forest departments. The early detection of forest fires is crucial, as once they reach a certain level, it is hard to control them. Compared with the satellite monitoring and detection of fire incidents, video-based fire detection on the ground identifies the fire at a faster rate. Hence, an unmanned aerial vehicle equipped with a GPS and a high-resolution camera can acquire quality images referencing the fire location. Further, deep learning frameworks can be applied to efficiently classify forest fires. In this paper, a cheaper UAV with extended MobileNet deep learning capability is proposed to classify forest fires (97.26%) and share the detection of forest fires and the GPS location with the state forest departments for timely action.
40
Wahyono, Agus Harjoko, Andi Dharmawan, Faisal Dharma Adhinata, Gamma Kosala, and Kang-Hyun Jo. "Real-Time Forest Fire Detection Framework Based on Artificial Intelligence Using Color Probability Model and Motion Feature Analysis." Fire 5, no. 1 (February 12, 2022): 23. http://dx.doi.org/10.3390/fire5010023.
Full textAbstract:
As part of the early warning system, forest fire detection has a critical role in detecting fire in a forest area to prevent damage to forest ecosystems. In this case, the speed of the detection process is the most critical factor to support a fast response by the authorities. Thus, this article proposes a new framework for fire detection based on combining color-motion-shape features with machine learning technology. The characteristics of the fire are not only red but also from their irregular shape and movement that tends to be constant at specific locations. These characteristics are represented by color probabilities in the segmentation stage, color histograms in the classification stage, and image moments in the verification stage. A frame-based evaluation and an intersection over union (IoU) ratio was applied to evaluate the proposed framework. Frame-based evaluation measures the performance in detecting fires. In contrast, the IoU ratio measures the performance in localizing the fires. The experiment found that the proposed framework produced 89.97% and 10.03% in the true-positive rate and the false-negative rate, respectively, using the VisiFire dataset. Meanwhile, the proposed method can obtain an average of 21.70 FPS in processing time. These results proved that the proposed method is fast in the detection process and can maintain performance accuracy. Thus, the proposed method is suitable and reliable for integrating into the early warning system.
41
Zhang, Q., Y. C. Wang, C. Soutis, and M. Gresil. "Development of a fire detection and suppression system for a smart air cargo container." Aeronautical Journal 125, no. 1283 (October 1, 2020): 205–22. http://dx.doi.org/10.1017/aer.2020.89.
Full textAbstract:
ABSTRACTThis study investigates and proposes a fire detection and suppression system for a smart air cargo container. A series of smoke spread and fire evolution numerical models are executed to assess the performance of container-based fire detection in various fire scenarios. This is to identify the worst case and optimise the location and threshold setting of fire detection sensors, achieving the shortest detection time. It is found that the fire detection threshold (reduction in light transmission = 12%/ft) for a container-based system can be set at three times the standard activation threshold for a cargo-based fire detection system, which can reduce the number of false alarms by three orders of magnitude. Moreover, effectiveness analysis of passive fire protection for the glass fibre-reinforced polymer-made smart container indicates an allowable leakage size of 0.01m2. The risk of internal overpressure has been found to be negligible for the leakage size required by aircraft pressure equalisation.
42
Gebert, Krista M., David E. Calkin, and Jonathan Yoder. "Estimating Suppression Expenditures for Individual Large Wildland Fires." Western Journal of Applied Forestry 22, no. 3 (July 1, 2007): 188–96. http://dx.doi.org/10.1093/wjaf/22.3.188.
Full textAbstract:
Abstract The extreme cost of fighting wildland fires has brought fire suppression expenditures to the forefront of budgetary and policy debate in the United States. Inasmuch as large fires are responsible for the bulk of fire suppression expenditures, understanding fire characteristics that influence expenditures is important for both strategic fire planning and onsite fire management decisions. These characteristics then can be used to produce estimates of suppression expenditures for large wildland fires for use in wildland fire decision support or after-fire reviews. The primary objective of this research was to develop regression models that could be used to estimate expenditures on large wildland fires based on area burned, variables representing the fire environment, values at risk, resource availability, detection time, and National Forest System region. Variables having the largest influence on cost included fire intensity level, area burned, and total housing value within 20 mi of ignition. These equations were then used to predict suppression expenditures on a set of fiscal year 2005 Forest Service fires for the purpose of detecting “extreme” cost fires—those fires falling more than 1 or 2 SDs above or below their expected value.
43
Avazov, Kuldoshbay, An Eui Hyun, Alabdulwahab Abrar Sami Sami S, Azizbek Khaitov, Akmalbek Bobomirzaevich Abdusalomov, and Young Im Cho. "Forest Fire Detection and Notification Method Based on AI and IoT Approaches." Future Internet 15, no. 2 (January 31, 2023): 61. http://dx.doi.org/10.3390/fi15020061.
Full textAbstract:
There is a high risk of bushfire in spring and autumn, when the air is dry. Do not bring any flammable substances, such as matches or cigarettes. Cooking or wood fires are permitted only in designated areas. These are some of the regulations that are enforced when hiking or going to a vegetated forest. However, humans tend to disobey or disregard guidelines and the law. Therefore, to preemptively stop people from accidentally starting a fire, we created a technique that will allow early fire detection and classification to ensure the utmost safety of the living things in the forest. Some relevant studies on forest fire detection have been conducted in the past few years. However, there are still insufficient studies on early fire detection and notification systems for monitoring fire disasters in real time using advanced approaches. Therefore, we came up with a solution using the convergence of the Internet of Things (IoT) and You Only Look Once Version 5 (YOLOv5). The experimental results show that IoT devices were able to validate some of the falsely detected fires or undetected fires that YOLOv5 reported. This report is recorded and sent to the fire department for further verification and validation. Finally, we compared the performance of our method with those of recently reported fire detection approaches employing widely used performance matrices to test the achieved fire classification results.
44
Khan, Fawad, Zhiguang Xu, Junling Sun, Fazal Maula Khan, Adnan Ahmed, and Yan Zhao. "Recent Advances in Sensors for Fire Detection." Sensors 22, no. 9 (April 26, 2022): 3310. http://dx.doi.org/10.3390/s22093310.
Full textAbstract:
Fire is indeed one of the major contributing factors to fatalities, property damage, and economic disruption. A large number of fire incidents across the world cause devastation beyond measure and description every year. To minimalize their impacts, the implementation of innovative and effective fire early warning technologies is essential. Despite the fact that research publications on fire detection technology have addressed the issue to some extent, fire detection technology still confronts hurdles in decreasing false alerts, improving sensitivity and dynamic responsibility, and providing protection for costly and complicated installations. In this review, we aim to provide a comprehensive analysis of the current futuristic practices in the context of fire detection and monitoring strategies, with an emphasis on the methods of detecting fire through the continuous monitoring of variables, such as temperature, flame, gaseous content, and smoke, along with their respective benefits and drawbacks, measuring standards, and parameter measurement spans. Current research directions and challenges related to the technology of fire detection and future perspectives on fabricating advanced fire sensors are also provided. We hope such a review can provide inspiration for fire sensor research dedicated to the development of advanced fire detection techniques.
45
Hally, B., L. Wallace, K. Reinke, and S. Jones. "ASSESSMENT OF THE UTILITY OF THE ADVANCED HIMAWARI IMAGER TO DETECT ACTIVE FIRE OVER AUSTRALIA." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B8 (June 22, 2016): 65–71. http://dx.doi.org/10.5194/isprs-archives-xli-b8-65-2016.
Full textAbstract:
Wildfire detection and attribution is an issue of importance due to the socio-economic impact of fires in Australia. Early detection of fires allows emergency response agencies to make informed decisions in order to minimise loss of life and protect strategic resources in threatened areas. Until recently, the ability of land management authorities to accurately assess fire through satellite observations of Australia was limited to those made by polar orbiting satellites. The launch of the Japan Meteorological Agency (JMA) Himawari-8 satellite, with the 16-band Advanced Himawari Imager (AHI-8) onboard, in October 2014 presents a significant opportunity to improve the timeliness of satellite fire detection across Australia. The near real-time availability of images, at a ten minute frequency, may also provide contextual information (background temperature) leading to improvements in the assessment of fire characteristics. This paper investigates the application of the high frequency observation data supplied by this sensor for fire detection and attribution. As AHI-8 is a new sensor we have performed an analysis of the noise characteristics of the two spectral bands used for fire attribution across various land use types which occur in Australia. Using this information we have adapted existing algorithms, based upon least squares error minimisation and Kalman filtering, which utilise high frequency observations of surface temperature to detect and attribute fire. The fire detection and attribution information provided by these algorithms is then compared to existing satellite based fire products as well as in-situ information provided by land management agencies. These comparisons were made Australia-wide for an entire fire season - including many significant fire events (wildfires and prescribed burns). Preliminary detection results suggest that these methods for fire detection perform comparably to existing fire products and fire incident reporting from relevant fire authorities but with the advantage of being near-real time. Issues remain for detection due to cloud and smoke obscuration, along with validation of the attribution of fire characteristics using these algorithms.
46
Hally, B., L. Wallace, K. Reinke, and S. Jones. "ASSESSMENT OF THE UTILITY OF THE ADVANCED HIMAWARI IMAGER TO DETECT ACTIVE FIRE OVER AUSTRALIA." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B8 (June 22, 2016): 65–71. http://dx.doi.org/10.5194/isprsarchives-xli-b8-65-2016.
Full textAbstract:
Wildfire detection and attribution is an issue of importance due to the socio-economic impact of fires in Australia. Early detection of fires allows emergency response agencies to make informed decisions in order to minimise loss of life and protect strategic resources in threatened areas. Until recently, the ability of land management authorities to accurately assess fire through satellite observations of Australia was limited to those made by polar orbiting satellites. The launch of the Japan Meteorological Agency (JMA) Himawari-8 satellite, with the 16-band Advanced Himawari Imager (AHI-8) onboard, in October 2014 presents a significant opportunity to improve the timeliness of satellite fire detection across Australia. The near real-time availability of images, at a ten minute frequency, may also provide contextual information (background temperature) leading to improvements in the assessment of fire characteristics. This paper investigates the application of the high frequency observation data supplied by this sensor for fire detection and attribution. As AHI-8 is a new sensor we have performed an analysis of the noise characteristics of the two spectral bands used for fire attribution across various land use types which occur in Australia. Using this information we have adapted existing algorithms, based upon least squares error minimisation and Kalman filtering, which utilise high frequency observations of surface temperature to detect and attribute fire. The fire detection and attribution information provided by these algorithms is then compared to existing satellite based fire products as well as in-situ information provided by land management agencies. These comparisons were made Australia-wide for an entire fire season - including many significant fire events (wildfires and prescribed burns). Preliminary detection results suggest that these methods for fire detection perform comparably to existing fire products and fire incident reporting from relevant fire authorities but with the advantage of being near-real time. Issues remain for detection due to cloud and smoke obscuration, along with validation of the attribution of fire characteristics using these algorithms.
47
Morisette, Jeffrey T., Louis Giglio, Ivan Csiszar, Alberto Setzer, Wilfrid Schroeder, Douglas Morton, and Christopher O. Justice. "Validation of MODIS Active Fire Detection Products Derived from Two Algorithms." Earth Interactions 9, no. 9 (July 1, 2005): 1–25. http://dx.doi.org/10.1175/ei141.1.
Full textAbstract:
Abstract Fire influences global change and tropical ecosystems through its connection to land-cover dynamics, atmospheric composition, and the global carbon cycle. As such, the climate change community, the Brazilian government, and the Large-Scale Biosphere–Atmosphere (LBA) Experiment in Amazonia are interested in the use of satellites to monitor and quantify fire occurrence throughout Brazil. Because multiple satellites and algorithms are being utilized, it is important to quantify the accuracy of the derived products. In this paper the characteristics of two fire detection algorithms are evaluated, both of which are applied to Terra’s Moderate Resolution Imagine Spectroradiometer (MODIS) data and with both operationally producing publicly available fire locations. The two algorithms are NASA’s operational Earth Observing System (EOS) MODIS fire detection product and Brazil’s Instituto Nacional de Pesquisas Espaciais (INPE) algorithm. Both algorithms are compared to fire maps that are derived independently from 30-m spatial resolution Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) imagery. A quantitative comparison is accomplished through logistic regression and error matrices. Results show that the likelihood of MODIS fire detection, for either algorithm, is a function of both the number of ASTER fire pixels within the MODIS pixel as well as the contiguity of those pixels. Both algorithms have similar omission errors and each has a fairly high likelihood of detecting relatively small fires, as observed in the ASTER data. However, INPE’s commission error is roughly 3 times more than that of the EOS algorithm.
48
Lin, Hong, Zhen Ping Qiang, Guang Zhi Di, and Zhi Gang Liu. "Research on Detection Techniques of Early Forest Fire Based on Dynamic Characteristics of Smoke." Applied Mechanics and Materials 340 (July 2013): 431–35. http://dx.doi.org/10.4028/www.scientific.net/amm.340.431.
Full textAbstract:
The forest fire has been threatening the forest ecosystem and has brought huge economic losses to humans. Traditional fire detection systems use ion-optical smoking type and other physical or chemical means to discover a fire, which is not suitable for outdoor forest fires with long-distance and large-area characteristics. This paper presents the early fire detection algorithm based on smoke dynamic characteristics and its main part includes smoke color model, dynamic feature extraction and fire area connected component analysis. Through standard video database performance testing and compared to the algorithm and the traditional fire detection method, we can achieve early warning of a fire and can effectively reduce false and negative rate of fire monitoring system.
49
Begum, Sk Razeena, Yogananda Datta S, and Manoj M S V. "MASK R-CNN FOR FIRE DETECTION." International Research Journal of Computer Science 8, no. 7 (July 30, 2021): 145–51. http://dx.doi.org/10.26562/irjcs.2021.v0807.003.
Full textAbstract:
Object detection has an increasing amount of attention in recent years due to its wide range of applications and recent technological breakthroughs. Deep learning is the state-of-art method to perform object detection. This task is under extensive investigation in both academics and real-world applications such as security monitoring, autonomous driving, transportation surveillance, drone scene analysis, robotic vision, etc., It is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images or videos. It not only provides the classes of the objects in an image but also localizes them in that particular image. The location is given in the form of bounding boxes or centroids. Instance segmentation may be defined as the technique that gives fine inference separately for each object by predicting labels for every pixel of that object in the input image. Each pixel is labeled according to the object class within which it is enclosed. We deal with Mask Region-Based Convolutional Neural Network (Mask R-CNN) to implement instance segmentation and detection of fire in a video or an image which can be used in real-world such as automatic fire extinguisher and alert systems. The training was done using Mask R-CNN for object detection with ResNet-101 backbone, with a 0.001 learning rate and 2 images per GPU. With this, the proposed framework can detect fire using Mask Region-Based Convolutional Neural Network and can send immediate alert to the user if fire is detected
50
Lee, Hoon-Gi, Ui-Nam Son, Seung-Mo Je, Jun-Ho Huh, and Jae-Hun Lee. "Overview of Fire Prevention Technologies by Cause of Fire: Selection of Causes Based on Fire Statistics in the Republic of Korea." Processes 11, no. 1 (January 12, 2023): 244. http://dx.doi.org/10.3390/pr11010244.
Full textAbstract:
Every year, diverse types of safety accidents cause major damage to human life and property. In particular, failure to suppress safety accidents caused by fires during the early stages can lead to large-scale accidents, which in turn can cause more serious damage than other types of accident. Therefore, this paper presents an analysis of the prevailing research trends and future directions for research on preventing safety accidents due to fire. Since fire outbreaks can occur in many types of places, the study was conducted by selecting the places and causes involved in frequent fires, using fire data from Korea. As half of these fires were found to occur in buildings, this paper presents an analysis of the causes of building fires, and then focuses on three themes: fire prevention based on fire and gas detection; fire prevention in electrical appliances; and fire prevention for next-generation electricity. In the gas detection of the first theme, the gas referred to does not denote a specific gas, but rather to the gas used in each place. After an analysis of research trends for each issue related to fire prevention, future research directions are suggested on the basis of the findings. It is necessary to evaluate the risk, select a detection system, and improve its reliability in order to thoroughly prevent fires in the future. In addition, an active emergency response system should be developed by operating a fire prevention control system, and safety training should be developed after classifying the targets of the training targets appropriately.