To see the other types of publications on this topic, follow the link: Object detection using cascade AdaBoost method.
Journal articles on the topic 'Object detection using cascade AdaBoost method'
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 'Object detection using cascade AdaBoost method.'
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
Mustafa, Rashed, Yang Min, and Dingju Zhu. "Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier." Scientific World Journal 2014 (2014): 1–6. http://dx.doi.org/10.1155/2014/753860.
Full textAbstract:
Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research Gentle Adaboost (GAB) haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifier is suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier.
2
Sanjaya, Kadek Oki, Gede Indrawan, and Kadek Yota Ernanda Aryanto. "PENDETEKSIAN OBJEK ROKOK PADA VIDEO BERBASIS PENGOLAHAN CITRA DENGAN MENGGUNAKAN METODE HAAR CASCADE CLASSIFIER." International Journal of Natural Science and Engineering 1, no. 3 (2018): 92. http://dx.doi.org/10.23887/ijnse.v1i3.12938.
Full textAbstract:
Object detection is a topic widely studied by the scientists as a special study in image processing. Although applications of this topic have been implemented, but basically this technology is not yet mature, futher research is needed to developed to obtain the desired result. The aim of the present study is to detect cigarette objects on video by using the Viola Jones method (Haar Cascade Classifier). This method known to have speed and high accuracy because of combining some concept (Haar features, integral image, Adaboost, and Cascade Classifier) to be a main method to detect objects. In this research, detection testing of cigarettes object is in samples of video with the resolution 160x120 pixels, 320x240 pixels, 640x480 pixels under condition of on 1 cigarette object and condition 2 cigarettes object. The result of this research indicated that percentage of average accuracy highest 93.3% at condition 1 cigarette object and 86,7% in the condition 2 cigarette object that was detected on the video with resolution 640x480 pixels, while the percentage of accuracy lowest 90% at condition 1cigarette object, and 81,7% at the condition 2 cigarette objects, detected on the video with the lowest resolution 160x120 pixels. The percentage of average errors at detection cigarettes object was inversely with percentage of accuracy. So that the detection system is able to better recognize the object of the cigarette, then the number of samples in the database needs to be improved and able to represent various types of cigarettes under various conditions and can be added new parameters related to cigarette object
3
Utami, Febiannisa, Suhendri Suhendri, and Muhammad Abdul Mujib. "Implementasi Algoritma Haar Cascade pada Aplikasi Pengenalan Wajah." Journal of Information Technology 3, no. 1 (2021): 33–38. http://dx.doi.org/10.47292/joint.v3i1.45.
Full textAbstract:
The large number of citizens in an organization makes the development of an attendance system or citizen detection in a place important in the running of work activities in the organization. Utilization of an IP Camera which is only used for regular monitoring without further detection of the needs of citizens in the organization made the development of personnel detection developed for monitoring the presence of personnel. With the development of a face detection system, it is hoped that the facial algorithm development system will be developed using an IP Camera. Face detection has been developed which has many and special features which aim to determine whether or not a face has been detected in an image. With image management that is developed in face detection, detection will be faster and more accurate because the color is processed into gray degrees so that there are fewer color pixels than those with colors. By using the Python programming language and an image detection library called OpenCV, less code will be designed. This study uses the Viola Jones method, which is a fast and accurate face detection method developed by Paul Viola and Michael Jones. In this study, the Viola Jones method uses the Haar Cascade algorithm which functions as a detection feature in the system and is combined with the internal image process and the AdaBoost Learning and Cascade Classifier so that the detected face object will easily classify whether the object is a face or not. In this case the Cascade Classfier used in this study is the face and eyes. The development of this algorithm is carried out for face detection and recognition. The detection is done by taking pictures with the process taken using a webcam. The system will take several pictures and then the image data will be stored in a folder called dataSet. After that, all data is trained so that it can be recognized by the system. With retrieval, detection and recognition limitations that can only be taken from a distance of less than three meters, face detection on the IP Camera can still read objects other than faces. With recognition and accuracy on the webcam camera, about 80,5% this system can be developed with the Haar Cascade algorithm and the Haar Cascade algorithm precisely to be applied to the development of faced detection and face recognition. By developing the Haar Cascade algorithm for face detection, problems and utilization of an organization's data can be more easily detected and used by IP cameras that can support the performance process of face detection and recognition
4
Imanuddin, Imanuddin, Fachrid Alhadi, Raza Oktafian, and Ahmad Ihsan. "Deteksi Mata Mengantuk pada Pengemudi Mobil Menggunakan Metode Viola Jones." MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 18, no. 2 (2019): 321–29. http://dx.doi.org/10.30812/matrik.v18i2.389.
Full textAbstract:
Computer Vision is one of the branches of Image processing science that allows a combination of human beings, such as identifying an object like an eye and taking a decision. Many of the face detection systems use the Viola Jones method as an object detection method. The method of Viola Jones is known by having high speed and accuracy because it is useful to combine several concepts such as (Haar Features, Integral Image, AdaBoost, and Cascade Classifier) into a major method for detecting objects. The programming language used in this study uses the MATLAB programming language to facilitate the process of creating the system. The research aims to implement Viola Jones into a simple eye-sensing drowsiness system by utilizing the existing libraries in the MATLAB programming language. Once the system is completed, a system test is performed against the detected drowsiness detection characteristics. This eye drowsiness detection system aims to determine if the car rider is sleepy or not when driving with an input in the form of eye detection taken using a digital camera and then inserted into a language Programming GUI Matlab where the value is taken binary eyes, sleepy eyes and not sleepy that will be a reference that will be processed later so that it can produce the output of a warning sound to the rider of the sleepy car vehicle or not The sleepy automatically. The testing of the program gained an amount detected 7 eyes of 10 eyes by using BW 0255 level which is useful to accelerate a program to detect sleepy eyes.
5
Hu, Hongyu, Pengfei Tao, Zhenhai Gao, Qingnian Wang, Zhihui Li, and Zhaowei Qu. "Vision-Based Bicycle Detection Using Multiscale Block Local Binary Pattern." Mathematical Problems in Engineering 2014 (2014): 1–7. http://dx.doi.org/10.1155/2014/370685.
Full textAbstract:
Bicycle traffic has heavy proportion among all travel modes in some developing countries, which is crucial for urban traffic control and management as well as facility design. This paper proposes a real-time multiple bicycle detection algorithm based on video. At first, an effective feature called multiscale block local binary pattern (MBLBP) is extracted for representing the moving object, which is a well-classified feature to distinguish between bicycles and nonbicycles; then, a cascaded bicycle classifier trained by AdaBoost algorithm is proposed, which has a good computation efficiency. Finally, the method is tested with video sequence captured from the real-world traffic scenario. The bicycles in the test scenario are successfully detected.
6
Yan, Shi-Xian, Peng-Fei Zhao, Xin-Yu Gao, et al. "Microscopic Object Recognition and Localization Based on Multi-Feature Fusion for In-Situ Measurement In Vivo." Algorithms 12, no. 11 (2019): 238. http://dx.doi.org/10.3390/a12110238.
Full textAbstract:
Microscopic object recognition and analysis is very important in micromanipulation. Micromanipulation has been extensively used in many fields, e.g., micro-assembly operation, microsurgery, agriculture, and biological research. Conducting micro-object recognition in the in-situ measurement of tissue, e.g., in the ion flux measurement by moving an ion-selective microelectrode (ISME), is a complex problem. For living tissues growing at a rate, it remains a challenge to accurately recognize and locate an ISME to protect living tissues and to prevent an ISME from being damaged. Thus, we proposed a robust and fast recognition method based on local binary pattern (LBP) and Haar-like features fusion by training a cascade of classifiers using the gentle AdaBoost algorithm to recognize microscopic objects. Then, we could locate the electrode tip from the background with strong noise by using the Hough transform and edge extraction with an improved contour detection method. Finally, the method could be used to automatically and accurately calculate the relative distance between the two micro-objects in the microscopic image. The results show that the proposed method can achieve good performance in micro-object recognition with a recognition rate up to 99.14% and a tip recognition speed up to 14 frames/s at a resolution of 1360 × 1024. The max error of tip positioning is 6.10 μm, which meets the design requirements of the ISME system. Furthermore, this study provides an effective visual guidance method for micromanipulation, which can facilitate automated micromanipulation research.
7
Prastowo, Bambang Nurcahyo, Nur Achmad Sulistyo Putro, Oktaf Agni Dhewa, and Ach Maulana Habibi Yusuf. "Pengenalan Personal Menggunakan Citra Tampak Atas pada Lingkungan Cashierless Strore." Jurnal Buana Informatika 10, no. 1 (2019): 19. http://dx.doi.org/10.24002/jbi.v10i1.1779.
Full textAbstract:
Personal recognition with image processing techniques from the side view has the disadvantage of being applied to the cashierless store environment, namely inaccurate recognition or identification when personal collisions occur. To overcome this, the image capture method is used from the top-view. Personal recognition method through the top-view image using the Haar Cascade Classifier method. 1420 positive images and 2170 negative images are used to find features that are considered suitable for recognizing objects using the Adaptive Boosting (Adaboost) method. Tests were carried out on 100 test data by varying the parameters of min_neighbors (3.4, and 5) and the size of the dataset window (25x25, 35x35, 45x45 pixels). Personal recognition testing gets the highest accuracy of 89.9% with the parameters used are min_neighbors 5 and the size of the 25x25 pixel dataset in the detection parameter size of min_size 140x140 pixels.
8
Duan, Li Juan, Ze Cheng Sun, Chun Peng Wu, Xue Bin Wang, Zhen Yang, and Jian Li. "Adult Image Detection Based on AdaBoost." Advanced Materials Research 562-564 (August 2012): 1693–96. http://dx.doi.org/10.4028/www.scientific.net/amr.562-564.1693.
Full textAbstract:
In this paper, a method of detecting adult images based on AdaBoost was proposed. We focused on the detection of the adult images that have naked breasts or naked genitalia. By using basic and rotated Haar-like features extracted from the samples in the training set, we trained a cascade detector. The detector would classify the image whether to be a pornographic one or not. The results showed that this method achieved a high detection rate and a low false alarm rate.
9
Yuan, Xue, Xue Ye Wei, and Yong Duan Song. "Performance Improvement on Edge-Based Human Detection Using Local Contrast Enhancement." Advanced Materials Research 383-390 (November 2011): 615–20. http://dx.doi.org/10.4028/www.scientific.net/amr.383-390.615.
Full textAbstract:
This paper presents a local contrast enhancement method, which is able to improve the detection performance of edge-based human detection. First, a neighborhood dependent local contrast enhancement method is used to enhance the images contrast. Next, the cascade AdaBoost classifier is used to discriminate between human and non-human. Experimental results show that the performance of our method is about 5% better than that of the conventional method.
10
Wen-Chang Cheng and Ding-Mao Jhan. "Triaxial Accelerometer-Based Fall Detection Method Using a Self-Constructing Cascade-AdaBoost-SVM Classifier." IEEE Journal of Biomedical and Health Informatics 17, no. 2 (2013): 411–19. http://dx.doi.org/10.1109/jbhi.2012.2237034.
Full text
11
Pavani, K. "Novel Vehicle Detection in Real Time Road Traffic Density Using Haar Cascade Comparing with KNN Algorithm based on Accuracy and Time Mean Speed." Revista Gestão Inovação e Tecnologias 11, no. 2 (2021): 897–910. http://dx.doi.org/10.47059/revistageintec.v11i2.1723.
Full textAbstract:
Aim: The main objective of the paper is to detect objects in iconic real time traffic density videos from CCTVs and Cameras using Haar Cascade algorithm and to compare algorithms with K-Nearest Neighbour algorithm (KNN). In this case we tried improving the rate of accuracy in predicting the traffic density. Materials and methods: Haar Cascade algorithm is applied on 5 realistic videos and which consists of more than 250 frames. For the same we evaluated the Accuracy and Precision values. Harr-like function displays the vehicle’s visual structure, and the AdaBoost machine learning algorithm was used to create a classifier by combining individual classifiers. The significance value achieved for finding the accuracy and precision was 0.445 and 0.754 respectively. Results and Discussions: Detection of vehicles in high speed videos is performed by using Haar Cascade which has mean accuracy with 85.22% and mean precision with 90.63% and 60% of mean accuracy and 58.53% mean precision in KNN classifiers. Conclusion: The performance of the Haar Cascade appears to be better than KNN in terms of both Accuracy and Precision.
12
Bai, Zhong Hao, Zhi Peng Ding, and Qiang Yan. "Study on the Method of Pedestrian Detection in Automobile Safety System." Advanced Materials Research 580 (October 2012): 118–21. http://dx.doi.org/10.4028/www.scientific.net/amr.580.118.
Full textAbstract:
In order to improve automobile active safety performance, and reduce the traffic accidents between pedestrians and vehicles, a pedestrian detection method combined with pedestrian contour features is proposed based on the combination of the reliable Adaboost and SVM. For the requirements of fast and accurate pedestrian detection system, ten types of haar-like features are given as the coarse features firstly, and which are trained through Adaboost cascade algorithm to ensure the system with a high detection speed. Then, the hog features of strong ability to distinguish pedestrians are selected as the fine features, and the pedestrian classifier is got by using SVM of different kernels to improve the detection accuracy. It is shown that the method has a higher detection rate and achieves a better detection effect.
13
Hsia, Chih Hsien, Jen Shiun Chiang, and Chin Yi Lin. "Illumination Variant Face Detection System Using Hierarchical Feature Method." Applied Mechanics and Materials 764-765 (May 2015): 1309–13. http://dx.doi.org/10.4028/www.scientific.net/amm.764-765.1309.
Full textAbstract:
In this study, we propose a new solution based on Adaboost algorithm and Back Propagation Network (BPN) of Neural Network (NN) combining local and global features with cascade architecture to detect human faces. We use Modified Census Transform (MCT) feature that belong to texture features and is less sensitive to illumination for local feature calculation. By this approach, it is not necessary to preprocess each sub-window of the image. For classification, we use the structure of hierarchical feature to control the number of features. With only MCT, it is easy to misjudge faces, and therefore in this work we include the brightness information of global features to eliminate the false positive regions. As a result, the proposed approach can have Detection Rate (DR) of 99%, false positives of only 11, and detection speed of 27.92 Frame Per Second (FPS).
14
Chang, Chuang Jan, and Shu Lin Hwang. "LSO-AdaBoost Based Face Detection for IP-CAM Video." Applied Mechanics and Materials 284-287 (January 2013): 3543–48. http://dx.doi.org/10.4028/www.scientific.net/amm.284-287.3543.
Full textAbstract:
The IP-CAM plays a major role in the context of digital video surveillance systems. The function of face detection can add extra value and can contribute towards an intelligent video surveillance system. The cascaded AdaBoost-based face detection system proposed by Viola can support real-time detection with a high detection rate. The performance of the Alt2 cascade (from OpenCV) in an IP-CAM video is worse than that with regard to static images because the training data set in the Alt2 cannot consider the localized characters in the special IP-CAM video. Therefore, this study presents an enhanced training method using the Adaboost algorithm which is capable of obtaining the localized sampling optimum (LSO) from a local IP-CAM video. In addition, we use an improved motion detection algorithm that cooperates with the former face detector to speed up processing time and achieve a better detection rate on video-rate processing speed. The proposed solution has been developed around the cascaded AdaBoost approach, using the open-CV library, with a LSO from a local IP-CAM video. An efficient motion detection model is adopted for practical applications. The overall system performance using 30% local samples can be improved to a 97.9% detection rate and reduce detection time by 54.5% with regard to the Alt2 cascade.
15
Putri, Rizka Eka, Tekad Matulatan, and Nurul Hayaty. "Sistem Deteksi Wajah Pada Kamera Realtime dengan menggunakan Metode Viola Jones." Jurnal Sustainable: Jurnal Hasil Penelitian dan Industri Terapan 8, no. 1 (2019): 30–37. http://dx.doi.org/10.31629/sustainable.v8i1.526.
Full textAbstract:
In general, human are given the mind and mind to be able to determine or be able to didtinguish individuals who appear either human, animal, plant, and other objects that are known or unknown. And it is possible for human to recognize these object from their sight and from their brain memory. Especially on the human face, human can recognize whether the object is human or not human, and can recognize the object very well through his own eyes.face detection system in human becomes very important in the development of science of digital image processing. The research has been done with many advantages and disadvantages. From a face many information features that can be read, such as eyes, nose, and mouth. The detection system uses Viola Jones method as an object detection method. The Viola Jones method is known to have considerable Speed and accuracy as it combines several concepts (Haar feature, Integral image, Adaboost, Cascade classifier) into a main method for detecting objects.Based on tests conducted on face identification under conditions that may affect face detection results, the results show an accuracy of 67,6 % to detect the face.
16
Wu, Wen Huan, Ying Jun Zhao, and Yong Fei Che. "Research and Implementation of Face Detection Based on OpenCV." Advanced Materials Research 971-973 (June 2014): 1710–13. http://dx.doi.org/10.4028/www.scientific.net/amr.971-973.1710.
Full textAbstract:
Face detection is the key point in automatic face recognition system. This paper introduces the face detection algorithm with a cascade of Adaboost classifiers and how to configure OpenCV in MCVS. Using OpenCV realized the face detection. And a detailed analysis of the face detection results is presented. Through experiment, we found that the method used in this article has a high accuracy rate and better real-time.
17
Zhang, Liyuan, Jiashi Zhao, Zhengang Jiang, and Huamin Yang. "Intelligent Measurement of Spinal Curvature Using Cascade Gentle AdaBoost Classifier and Region-Based DRLSE." Journal of Advanced Computational Intelligence and Intelligent Informatics 23, no. 3 (2019): 502–11. http://dx.doi.org/10.20965/jaciii.2019.p0502.
Full textAbstract:
For spinal curvature measurements, because of the anatomical complexity of the spine CT image, developing an automated method to avoid manual landmark is a challenging task. In this study, we propose an intelligent framework that integrates the cascade AdaBoost classifier and region-based distance regularized level set evolution (DRLSE) with the vertebral centroid measurement. First, the histogram-of-oriented-gradients based cascade gentle AdaBoost classifier is used to detect automatically and localize vertebral bodies from computer tomography (CT) spinal images. Considering these vertebral pathological images enables us to produce a diverse training dataset. Then, the DRLSE method introduces the local region information to converge the vertebral boundary quickly. The located bounding box is regarded as an accurate initial contour. This avoids the negative impact of manual initialization. Finally, we perform vertebral centroid extraction and spinal curve fitting. The spinal curvature angle is determined by calculating the angle between two tangents to the curve. We verified the effectiveness of the proposed method on 10 spine CT volumes. Quantitative comparison against the ground-truth centroids yielded a detection accuracy rate of 98.3% and a mean centroid location error of 1.15 mm. The comparative results with existing methods demonstrate that the proposed method can accurately detect and segment vertebral bodies. Furthermore, the spinal curvature can be automatically measured without manual landmark.
18
Zulfikri, Muhammad, Erni Yudaningtyas, and Rahmadwati Rahmadwati. "Sistem Penegakan Speed Bump Berdasarkan Kecepatan Kendaraan yang Diklasifikasikan Haar Cascade Classifier." Jurnal Teknologi dan Sistem Komputer 7, no. 1 (2019): 12–18. http://dx.doi.org/10.14710/jtsiskom.7.1.2019.12-18.
Full textAbstract:
Driving at high speed is among the frequent causes of accidents. In this research, a warning system was developed to warn drivers when their speed beyond the safety limit. Haar cascade classifier was proposed for the detection system which comprises Haar features, integral image, AdaBoost learning, and cascade classifier. The system was implemented using Python OpenCV library and evaluated on road traffic video collected in one way traffic. As a result, the proposed method yields 97.92% of car detection accuracy in daylight and MSE of 2.88 in speed measurement.
19
Chau, Khanh Ngan, and Nghi Thanh Doan. "DENSE SIFT FEATURE AND LOCAL NAIVE BAYES NEAREST NEIGHBOR FOR FACE RECOGNITION." Scientific Journal of Tra Vinh University 1, no. 28 (2017): 56–63. http://dx.doi.org/10.35382/18594816.1.28.2017.46.
Full textAbstract:
Human face recognition is a technology which is widely used in life. There have been much effort on developing face recognition algorithms. In this paper, we present a new methodology that combines Haar Like Features - Cascade of Boosted Classifiers, Dense Scale-Invariant Feature Transform (DSIFT), Local Naive Bayes Nearest Neighbor (LNBNN) algorithm for the recognition of human face. We use Haar Like Features and the combination of AdaBoost algorithm and Cascade stratified model to detect and extract the face image, the DSIFT descriptors of the image are computed only for the aligned and cropped face image.Then, we apply the LNBNN algorithms for object recognition. Numerical testing on several benchmark datasets using our proposed method for facerecognition gives the better results than other methods. The accuracies obtained by LNBNN method is 99.74 %.
20
Aoyagi, Seiji, Nobuhiko Hattori, Atsushi Kohama, et al. "Object Detection and Recognition Using Template Matching with SIFT Features Assisted by Invisible Floor Marks." Journal of Robotics and Mechatronics 21, no. 6 (2009): 689–97. http://dx.doi.org/10.20965/jrm.2009.p0689.
Full textAbstract:
For simultaneously localizing and mapping (SLAM) an indoor mobile robot, a method to process a monocular image of entire environmental view is proposed. To ensure that an object can be searched for, invisible floor marks are proposed for modifying the environment and which are useful in narrowing the search area in an image. Specifically our approach involves: 1) narrowing the searched area using invisible floor marks, 2) extracting features based on scale-invariant feature transform (SIFT), 3) using template matching with SIFT features assisted by partial templates and the spatial relationship to the floor, and 4) verifying object recognition with an AdaBoost classifier using Haar-like features based on object shape information. A robot is localized relative to the floor using the floor marks, then, objects in a clattered image are extracted and recognized, and 3D solid models of them are mapped on the floor to build a highly structured 3D map. Recognition was over 80% successful, including tables and chairs and taking several tens of seconds per 640 × 480 pixel image.
21
Bai, Ting, Kaimin Sun, Wenzhuo Li, Deren Li, Yepei Chen, and Haigang Sui. "A Novel Class-Specific Object-Based Method for Urban Change Detection Using High-Resolution Remote Sensing Imagery." Photogrammetric Engineering & Remote Sensing 87, no. 4 (2021): 249–62. http://dx.doi.org/10.14358/pers.87.4.249.
Full textAbstract:
A single-scale object-based change-detection classifier can distinguish only global changes in land cover, not the more granular and local changes in urban areas. To overcome this issue, a novel class-specific object-based change-detection method is proposed. This method includes three steps: class-specific scale selection, class-specific classifier selection, and land cover change detection. The first step combines multi-resolution segmentation and a random forest to select the optimal scale for each change type in land cover. The second step links multi-scale hierarchical sampling with a classifier such as random forest, support vector machine, gradient-boosting decision tree, or Adaboost; the algorithm automatically selects the optimal classifier for each change type in land cover. The final step employs the optimal classifier to detect binary changes and from-to changes for each change type in land cover. To validate the proposed method, we applied it to two high-resolution data sets in urban areas and compared the change-detection results of our proposed method with that of principal component analysis k-means, object-based change vector analysis, and support vector machine. The experimental results show that our proposed method is more accurate than the other methods. The proposed method can address the high levels of complexity found in urban areas, although it requires historical land cover maps as auxiliary data.
22
Lu, Biao, Nannan Liang, Chengfang Tan, and Zhenggao Pan. "Markov Chain and Adaboost Image Saliency Detection Algorithm Based on Conditional Random Field." International Journal of Circuits, Systems and Signal Processing 15 (July 30, 2021): 762–73. http://dx.doi.org/10.46300/9106.2021.15.84.
Full textAbstract:
The traditional salient object detection algorithms are used to apply the underlying features and prior knowledge of the images. Based on conditional random field Markov chain and Adaboost image saliency detection technology, a saliency detection method is proposed to effectively reduce the error caused by the target approaching the edge, which mainly includes the use of absorption Markov chain model to generate the initial saliency map. In this model, the transition probability of each node is defined by the difference of color and texture between each super pixel, and the absorption time of the transition node is calculated as the significant value of each super pixel. A strong classifier optimization model based on Adaboost iterative algorithm is designed.The initial saliency map is processed by the classifier to obtain an optimized saliency map, which highlights the global contrast. In order to extract the saliency region of the final saliency map, a method using conditional random field is designed to segment and extract the saliency region. The results show that the saliency area detected by this method is prominent, the overall contour is clear and has high resolution. At the same time, this method has better performance in accuracy recall curve and histogram.
23
Zhao, Linghua, and Zhihua Huang. "A Moving Object Detection Method Using Deep Learning-Based Wireless Sensor Networks." Complexity 2021 (April 12, 2021): 1–12. http://dx.doi.org/10.1155/2021/5518196.
Full textAbstract:
Aiming at the problem of real-time detection and location of moving objects, the deep learning algorithm is used to detect moving objects in complex situations. In this paper, based on the deep learning algorithm of wireless sensor networks, a novel target motion detection method is proposed. This method uses the deep learning model to extract visual potential representation features through offline similarity function ranking learning and online model incremental update and uses the hierarchical clustering algorithm to achieve target detection and positioning; the low-precision histogram and high-precision histogram cascade the method which determines the correct position of the target and achieves the purpose of detecting the moving target. In order to verify the advantages and disadvantages of the deep learning algorithm compared with traditional moving object detection methods, a large number of comparative experiments are carried out, and the experimental results were analyzed qualitatively and quantitatively from a statistical perspective. The results show that, compared with the traditional methods, the deep learning algorithm based on the wireless sensor network proposed in this paper is more efficient. The detection and positioning method do not produce the error accumulation phenomenon and has significant advantages and robustness. The moving target can be accurately detected with a small computational cost.
24
Stevanović, Dušan. "OBJECT DETECTION USING VIOLA-JONES ALGORITHM." Knowledge International Journal 28, no. 4 (2018): 1349–54. http://dx.doi.org/10.35120/kij28041349d.
Full textAbstract:
In this paper it has been described and applied method for detecting face and face parts in images using the Viola-Jones algorithm. The work is based on Computer Vision Systems, artificial intelligence that deals with the recognition of two-dimensional or three-dimensional objects. When Cascade Object Detector script is trained, multimedia content is assigned for recognition. In this work the content will be in the form of an image, where the program will have the task of recognizing the objects in the images, separating the parts of the images in the head area, and on each discovered face, separately mark the area around the eyes, nose and mouth.Algorithm for detection and recognition is based on scanning and analyzing front part of human head. Common usage of face detection and recognition can be find in biometry, photography, on autofocus option which is implemented in professional photo cameras or on smiling detectors (Keller, 2007). Marketing is also popular field where face detection and recognition can be used. For example, web cameras that are implemented in TVs, can detect every face in near area. Calculating different type of algorithms and parameters, based on sex, age, ethnicity, system can play precisely segmented television commercials and campaigns. Example of that kind of systems is OptimEyes. (Strasburger, 2013)In other words, every algorithm that has as its main goal to detect and recognize face from image, should give as a feedback information, is there any face and if answer is positive, where is its location on image. In order to achieve acceptable performances, algorithm should minimize false recognitions. These are the cases when the algorithm ignores and does not recognize the real object from the image, and vice versa, when the wrong object is recognized as real. One of the algorithms that is frequently applied in this area of research is the Viola-Jones algorithm. This algorithm is functional in real time, meaning that besides detection, it is also possible to adjust the ability to monitor faces from video material.In this paper, the problem that will be analyzed is facial image detection. Man can do this task in a very simple way, but to do the same with a computer, it is necessary to have a range of precise and accurate information, formulas, methods and techniques. In order to maximize the precision of recognizing the face of the image using the Viola-Jones algorithm, it is desirable that the objects in the images are completely face-to-face with the image-taking device, which will be shown through experiments.
25
Cao, Lai Cheng, Wei Han, and Sheng Dong. "A New Intrusion Detection Method Based on Machine Learning in Mobile Ad Hoc NETwork." Applied Mechanics and Materials 548-549 (April 2014): 1304–10. http://dx.doi.org/10.4028/www.scientific.net/amm.548-549.1304.
Full textAbstract:
In a Mobile Ad hoc NETwork (MANET), intrusion detection is of significant importance in many applications in detecting malicious or unexpected intruder (s). The intruder can be an enemy in a battlefield, or a malicious moving object in the area of interest. Unfortunately, many anomaly intrusion detection systems (IDS) take on higher false alarm rate (FAR) and false negative rate (FNR). In this paper, we propose and implement a new intrusion-detection system using Adaboost, a prevailing machine learning algorithm, and its detecting model adopts a dynamic load-balancing algorithm, which can avoid packet loss and false negatives in high-performance severs with handling heavy traffic loads in real-time and can enhance the efficiency of detecting work. Compared to contemporary approaches, our system demonstrates an especially low false positive rate and false negative rate in certain circumstances while does not greatly affect the network performance.
26
Zhou, Zihan, Qinghan Lai, Shuai Ding, and Song Liu. "Novel Joint Object Detection Algorithm Using Cascading Parallel Detectors." Symmetry 13, no. 1 (2021): 137. http://dx.doi.org/10.3390/sym13010137.
Full textAbstract:
Object detection is an essential computer vision task that aims to detect target objects from an image. The traditional models are insufficient to generate a high-quality anchor box. To solve the problem, we propose a novel joint model called guided anchoring Region proposal networks and Cascading Grid Region Convolutional Neural Networks (RCGrid R-CNN), enhancing the ability of object detection. Our proposed model design is a joint object detection algorithm containing an anchor-based and an anchor-free branch in parallel and symmetry. In the anchor-based, we use nine-point spatial information fusion to obtain better anchor box location and introduce the shape prediction method of Guided Anchoring Region Proposal Networks (GA-RPN) to enhance the accuracy of the predicted anchor box. In the anchor-free branch, we introduce the Feature Selective Anchor-Free module (FSAF) to reduce the overlapping anchor boxes to obtain a more accurate anchor box. Furthermore, inspired by cascading theory, we cascade the new-designed detectors to improve the ability of object detection by setting a gradually increasing Intersection over Union (IoU) threshold. Compared with typical baseline models, we comprehensively evaluated our model by conducting experiments on two open datasets: Pascal VOC2007 and COCO2017. The experimental results demonstrate the effectiveness of RCGrid R-CNN in producing a high-quality anchor box.
27
Alreshidi, Abdulrahman, and Mohib Ullah. "Facial Emotion Recognition Using Hybrid Features." Informatics 7, no. 1 (2020): 6. http://dx.doi.org/10.3390/informatics7010006.
Full textAbstract:
Facial emotion recognition is a crucial task for human-computer interaction, autonomous vehicles, and a multitude of multimedia applications. In this paper, we propose a modular framework for human facial emotions’ recognition. The framework consists of two machine learning algorithms (for detection and classification) that could be trained offline for real-time applications. Initially, we detect faces in the images by exploring the AdaBoost cascade classifiers. We then extract neighborhood difference features (NDF), which represent the features of a face based on localized appearance information. The NDF models different patterns based on the relationships between neighboring regions themselves instead of considering only intensity information. The study is focused on the seven most important facial expressions that are extensively used in day-to-day life. However, due to the modular design of the framework, it can be extended to classify N number of facial expressions. For facial expression classification, we train a random forest classifier with a latent emotional state that takes care of the mis-/false detection. Additionally, the proposed method is independent of gender and facial skin color for emotion recognition. Moreover, due to the intrinsic design of NDF, the proposed method is illumination and orientation invariant. We evaluate our method on different benchmark datasets and compare it with five reference methods. In terms of accuracy, the proposed method gives 13% and 24% better results than the reference methods on the static facial expressions in the wild (SFEW) and real-world affective faces (RAF) datasets, respectively.
28
Mekonnen, Alhayat Ali, Frédéric Lerasle, Ariane Herbulot, and Cyril Briand. "Incorporating Computation Time Measures During Heterogeneous Features Selection in a Boosted Cascade People Detector." International Journal of Pattern Recognition and Artificial Intelligence 30, no. 08 (2016): 1655022. http://dx.doi.org/10.1142/s0218001416550223.
Full textAbstract:
In this paper, we investigate the notion of incorporating feature computation time (CT) measures during feature selection in a boosted cascade people detector utilizing heterogeneous pool of features. We present various approaches based on pareto-front analysis, CT weighted adaboost, and Binary Integer Programming (BIP) with comparative evaluations. The novel feature selection method proposed based on BIP — the main contribution — mines heterogeneous features taking both detection performance and CT explicitly into consideration. The results demonstrate that the detector using this feature selection scheme exhibits low miss rates (MRs) with significant boost in frame rate. For example, it achieves a [Formula: see text] less MR at [Formula: see text] FPPW compared to Dalal and Triggs HOG detector with a [Formula: see text]x speed improvement. The presented extensive experimental results clearly highlight the improvements the proposed framework brings to the table.
29
Atmaja, Gusti Ngurah Rama Putra, Koredianto Usman, and Muhammad Ary Murti. "THE CALCULATION SYSTEM OF NUMBER OF PEOPLE IN A ROOM BASED ON HUMAN DETECTION USING HAAR-CASCADE CLASSIFIER." Jurnal Teknik Informatika (Jutif) 2, no. 2 (2021): 75–84. http://dx.doi.org/10.20884/1.jutif.2021.2.2.83.
Full textAbstract:
Data of number of people in the room, calculations are usually carried out by assigning someone to oversee a room. In this final project, a system for calculating the number of people in the room is designed with image processing based on human detection that can be used in rooms, both for commercial applications and for security. This system uses Raspberry Pi device that already has an image processing method Haar-Cascade Classifier. Input data is in the form of video taken directly via webcam to be captured into a frame so that it can be used as a input the Haar-Cascade Classifier method and perform the counting process will be sent to the Antares platform. The system design has been tested with five scenarios. Scenario 1 the effect of the distance of the object, scenario 2 the effect of the pose of the object, scenario 3 the effect of the amount the object in the frame, scenario 4 affects the scale factor and scenario 5 measurement computation time. Scenarios 1 to 3 will do the best configuration for minimum neighbour. The system gets the best accuracy of 98,5% when the object distance 4 meters, the best accuracy of 96,6% when the object is facing forward and accuracy the best is 97,7% when the object in the frame is more than two objects with the best configuration use the minimum neighbour 5. Scenario 4 gets accuracy the best is 76,2% when using the scale factor 1.1. Scenario 5 gets the average computation time of the system is under one second, meaning the detection process done pretty fast.
30
Higashino, Shin-Ichiro, Toru Teruya, and Kazuhiko Yamada. "Position Identification Using Image Processing for UAV Flights in Martian Atmosphere." Journal of Robotics and Mechatronics 33, no. 2 (2021): 254–62. http://dx.doi.org/10.20965/jrm.2021.p0254.
Full textAbstract:
This paper presents a method for the position identification of an unmanned aerial vehicle (UAV) in the Martian atmosphere in the future. It uses the image processing of craters captured via an onboard camera of the UAV and database images. The method is composed of two processes: individual crater detection using a cascade object detector and position identification using the recognition Taguchi (RT)-method. In crater detection, objects with shapes that resemble craters are detected regardless of their positions, and the positions of multiple detected craters are identified using the criterion variable D*, which is a normalized Mahalanobis distance. D* is calculated from several feature variables expressing the area ratios and relative positions of the detected craters in the RT-method.
31
Xu, Yuelei, Mingming Zhu, Shuai Li, Hongxiao Feng, Shiping Ma, and Jun Che. "End-to-End Airport Detection in Remote Sensing Images Combining Cascade Region Proposal Networks and Multi-Threshold Detection Networks." Remote Sensing 10, no. 10 (2018): 1516. http://dx.doi.org/10.3390/rs10101516.
Full textAbstract:
Fast and accurate airport detection in remote sensing images is important for many military and civilian applications. However, traditional airport detection methods have low detection rates, high false alarm rates and slow speeds. Due to the power convolutional neural networks in object-detection systems, an end-to-end airport detection method based on convolutional neural networks is proposed in this study. First, based on the common low-level visual features of natural images and airport remote sensing images, region-based convolutional neural networks are chosen to conduct transfer learning for airport images using a limited amount of data. Second, to further improve the detection rate and reduce the false alarm rate, the concepts of “divide and conquer” and “integral loss’’ are introduced to establish cascade region proposal networks and multi-threshold detection networks, respectively. Third, hard example mining is used to improve the object discrimination ability and the training efficiency of the network during sample training. Additionally, a cross-optimization strategy is employed to achieve convolution layer sharing between the cascade region proposal networks and the subsequent multi-threshold detection networks, and this approach significantly decreases the detection time. The results show that the method established in this study can accurately detect various types of airports in complex backgrounds with a higher detection rate, lower false alarm rate, and shorter detection time than existing airport detection methods.
32
Utaminingrum, Fitri, Renaldi Primaswara Praetya, and Yuita Arum Sari. "Image Processing for Rapidly Eye Detection based on Robust Haar Sliding Window." International Journal of Electrical and Computer Engineering (IJECE) 7, no. 2 (2017): 823. http://dx.doi.org/10.11591/ijece.v7i2.pp823-830.
Full textAbstract:
Object Detection using Haar Cascade Clasifier widely applied in several devices and applications as a medium of interaction between human and computer such as a tool control that utilizes the detection of eye movements. Obviously speed and precision in the detection process such as eyes, has an effect if implemented on a device. If the eye could not detect accurately, controlling device systems could reach bad detection as well. The proposed method can be used as an approach to detect the eye region of eye based on haar classifier method by means of modifying the direction of sliding window. In which, it was initially placed in the middle position of image on facial area by assuming the location of eyes area in the central region of the image. While the window region of conventional haar cascade scan the whole of image start from the left top corner. From the experiment by using our proposed method, it can speed up the the computation time and improve accuracy significantly reach to 92,4%.
33
Wu, Xin, Danfeng Hong, Pedram Ghamisi, Wei Li, and Ran Tao. "MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection." Remote Sensing 10, no. 12 (2018): 1990. http://dx.doi.org/10.3390/rs10121990.
Full textAbstract:
Geospatial object detection is a fundamental but challenging problem in the remote sensing community. Although deep learning has shown its power in extracting discriminative features, there is still room for improvement in its detection performance, particularly for objects with large ranges of variations in scale and direction. To this end, a novel approach, entitled multi-scale and rotation-insensitive convolutional channel features (MsRi-CCF), is proposed for geospatial object detection by integrating robust low-level feature generation, classifier generation with outlier removal, and detection with a power law. The low-level feature generation step consists of rotation-insensitive and multi-scale convolutional channel features, which were obtained by learning a regularized convolutional neural network (CNN) and integrating multi-scaled convolutional feature maps, followed by the fine-tuning of high-level connections in the CNN, respectively. Then, these generated features were fed into AdaBoost (chosen due to its lower computation and storage costs) with outlier removal to construct an object detection framework that facilitates robust classifier training. In the test phase, we adopted a log-space sampling approach instead of fine-scale sampling by using the fast feature pyramid strategy based on a computable power law. Extensive experimental results demonstrate that compared with several state-of-the-art baselines, the proposed MsRi-CCF approach yields better detection results, with 90.19% precision with the satellite dataset and 81.44% average precision with the NWPU VHR-10 datasets. Importantly, MsRi-CCF incurs no additional computational cost, which is only 0.92 s and 0.7 s per test image on the two datasets. Furthermore, we determined that most previous methods fail to gain an acceptable detection performance, particularly when they face several obstacles, such as deformations in objects (e.g., rotation, illumination, and scaling). Yet, these factors are effectively addressed by MsRi-CCF, yielding a robust geospatial object detection method.
34
Kim, Jong Bae. "Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera." Symmetry 11, no. 10 (2019): 1205. http://dx.doi.org/10.3390/sym11101205.
Full textAbstract:
In this paper a method for detecting and estimating the distance of a vehicle driving in front using a single black-box camera installed in a vehicle was proposed. In order to apply the proposed method to autonomous vehicles, it was required to reduce the throughput and speed-up the processing. To do this, the proposed method decomposed the input image into multiple-resolution images for real-time processing and then extracted the aggregated channel features (ACFs). The idea was to extract only the most important features from images at different resolutions symmetrically. A method of detecting an object and a method of estimating a vehicle’s distance from a bird’s eye view through inverse perspective mapping (IPM) were applied. In the proposed method, ACFs were used to generate the AdaBoost-based vehicle detector. The ACFs were extracted from the LUV color, edge gradient, and orientation (histograms of oriented gradients) of the input image. Subsequently, by applying IPM and transforming a 2D input image into 3D by generating an image projected in three dimensions, the distance between the detected vehicle and the autonomous vehicle was detected. The proposed method was applied in a real-world road environment and showed accurate results for vehicle detection and distance estimation in real-time processing. Thus, it was showed that our method is applicable to autonomous vehicles.
35
Li, Jin, Daifu Yan, Kuan Luan, Zeyu Li, and Hong Liang. "Deep Learning-Based Bird’s Nest Detection on Transmission Lines Using UAV Imagery." Applied Sciences 10, no. 18 (2020): 6147. http://dx.doi.org/10.3390/app10186147.
Full textAbstract:
In order to ensure the safety of transmission lines, the use of unmanned aerial vehicle (UAV) images for automatic object detection has important application prospects, such as the detection of birds’ nests. The traditional bird’s nest detection methods mainly include the study of morphological characteristics of the bird’s nest. These methods have poor applicability and low accuracy. In this work, we propose a deep learning-based birds’ nests automatic detection framework—region of interest (ROI) mining faster region-based convolutional neural networks (RCNN). First, the prior dimensions of anchors are obtained by using k-means clustering to improve the accuracy of coordinate boxes generation. Second, in order to balance the number of foreground and background samples in the training process, the focal loss function is introduced in the region proposal network (RPN) classification stage. Finally, the ROI mining module is added to solve the class imbalance problem in the classification stage, combined with the characteristics of difficult-to-classify bird’s nest samples in the UAV images. After parameter optimization and experimental verification, the deep learning-based bird’s nest automatic detection framework proposed in this work achieves high detection accuracy. In addition, the mean average precision (mAP) and formula 1 (F1) score of the proposed method are higher than the original faster RCNN and cascade RCNN. Our comparative analysis verifies the effectiveness of the proposed method.
36
Pan, Bin, Jianhao Tai, Qi Zheng, and Shanshan Zhao. "Cascade Convolutional Neural Network Based on Transfer-Learning for Aircraft Detection on High-Resolution Remote Sensing Images." Journal of Sensors 2017 (2017): 1–14. http://dx.doi.org/10.1155/2017/1796728.
Full textAbstract:
Aircraft detection from high-resolution remote sensing images is important for civil and military applications. Recently, detection methods based on deep learning have rapidly advanced. However, they require numerous samples to train the detection model and cannot be directly used to efficiently handle large-area remote sensing images. A weakly supervised learning method (WSLM) can detect a target with few samples. However, it cannot extract an adequate number of features, and the detection accuracy requires improvement. We propose a cascade convolutional neural network (CCNN) framework based on transfer-learning and geometric feature constraints (GFC) for aircraft detection. It achieves high accuracy and efficient detection with relatively few samples. A high-accuracy detection model is first obtained using transfer-learning to fine-tune pretrained models with few samples. Then, a GFC region proposal filtering method improves detection efficiency. The CCNN framework completes the aircraft detection for large-area remote sensing images. The framework first-level network is an image classifier, which filters the entire image, excluding most areas with no aircraft. The second-level network is an object detector, which rapidly detects aircraft from the first-level network output. Compared with WSLM, detection accuracy increased by 3.66%, false detection decreased by 64%, and missed detection decreased by 23.1%.
37
Griffin, Terence, Yu Cao, Benyuan Liu, Maria J. Brunette, and Xinzi Sun. "Object Detection and Instance Segmentation in Chest X-rays for Tuberculosis Screening." International Journal of Transdisciplinary Artificial Intelligence 3, no. 1 (2021): 1–24. http://dx.doi.org/10.35708/tai1870-126250.
Full textAbstract:
Tuberculosis (TB) is a highly contagious disease leading to the deaths of approximately 2 million people annually. TB primarily affects the lungs and is spread through the air when people cough, sneeze, or spit. Providing healthcare professionals with better information, at a faster pace, is essential for combating this disease, especially in Low and Middle Income Countries (LMICs) with resource-constrained health systems. In this paper we describe how using convolution neural networks (CNNs) with an object level annotated dataset of chest X-rays (CXRs) allows us to identify the location of pulmonary issues indicative of TB. We compare the performance of Faster R-nobreakdash-CNN, Mask R-nobreakdash-CNN, Cascade versions of each, and SOLOv2, demonstrating reasonable results with a small dataset. We present a method to reduce the false positive rate by comparing the location of a detected object with the known location of areas where the detected class is likely to occur in the lung. Our results show that object detection and instance segmentation of CXRs can be achieved with a dataset of high-quality, object level annotations, and could be used as part of an automated TB screening process. This work has the potential to improve the speed of TB diagnosis in LMICs, if properly integrated into the healthcare system and adapted to existing clinical workflows and local regulations.
38
Chayadevi, M. L., Sujith Madhyastha, K. N. Nisarga, H. Charitha, and B. Susharan. "Automated Teller Machine Security with Image Processing and Machine Learning Techniques." Journal of Computational and Theoretical Nanoscience 17, no. 9 (2020): 4473–81. http://dx.doi.org/10.1166/jctn.2020.9100.
Full textAbstract:
There are many scenarios in society with thefts and crimes involved in Automated Teller Machines (ATM). These events are increasing day-by-day and which is also increasing the complexities on the crime investigation agencies. In order to deal with these situations, we have proposed an automated security method inside ATMs using image processing techniques which can alert the concerned authorities immediately whenever these types of situations arise. Hybrid method with Viola-Jones algorithm has been used for face recognition along with the Haar-cascade features. In the case of objects such as knife, gun etc. inside an ATM, combination of SVM and random forest algorithms are used for object detection. TensorFlow with machines learning algorithms have been used in the hybrid methodology. Android application has been developed to prevent and alert the crimes and send alert messages to the concerned. Speech alert system is developed to assist blind and physically challenged people.
39
Zubov, I. G., and N. A. Obukhova. "Method for Automatic Determination of a 3D Trajectory of Vehicles in a Video Image." Journal of the Russian Universities. Radioelectronics 24, no. 3 (2021): 49–59. http://dx.doi.org/10.32603/1993-8985-2021-24-3-49-59.
Full textAbstract:
Introduction. An important part of an automotive unmanned vehicle (UV) control system is the environment analysis module. This module is based on various types of sensors, e.g. video cameras, lidars and radars. The development of computer and video technologies makes it possible to implement an environment analysis module using a single video camera as a sensor. This approach is expected to reduce the cost of the entire module. The main task in video image processing is to analyse the environment as a 3D scene. The 3D trajectory of an object, which takes into account its dimensions, angle of view and movement vector, as well as the vehicle pose in a video image, provides sufficient information for assessing the real interaction of objects. A basis for constructing a 3D trajectory is vehicle pose estimation.Aim. To develop an automatic method for estimating vehicle pose based on video data analysis from a single video camera.Materials and methods. An automatic method for vehicle pose estimation from a video image was proposed based on a cascade approach. The method includes vehicle detection, key points determination, segmentation and vehicle pose estimation. Vehicle detection and determination of its key points were resolved via a neural network. The segmentation of a vehicle video image and its mask preparation were implemented by transforming it into a polar coordinate system and searching for the outer contour using graph theory.Results. The estimation of vehicle pose was implemented by matching the Fourier image of vehicle mask signatures and the templates obtained based on 3D models. The correctness of the obtained vehicle pose and angle of view estimation was confirmed by experiments based on the proposed method. The vehicle pose estimation had an accuracy of 89 % on an open Carvana image dataset.Conclusion. A new approach for vehicle pose estimation was proposed, involving the transition from end-to-end learning of neural networks to resolve several problems at once, e.g., localization, classification, segmentation, and angle of view, towards cascade analysis of information. The accuracy level of end-to-end learning requires large sets of representative data, which complicates the scalability of solutions for road environments in Russia. The proposed method makes it possible to estimate the vehicle pose with a high accuracy level, at the same time as involving no large costs for manual data annotation and training.
40
Alexeev, Alexey, Georgy Kukharev, Yuri Matveev, and Anton Matveev. "A Highly Efficient Neural Network Solution for Automated Detection of Pointer Meters with Different Analog Scales Operating in Different Conditions." Mathematics 8, no. 7 (2020): 1104. http://dx.doi.org/10.3390/math8071104.
Full textAbstract:
We investigate a neural network–based solution for the Automatic Meter Reading detection problem, applied to analog dial gauges. We employ a convolutional neural network with a non-linear Network in Network kernel. Presently, there is a significant interest in systems for automatic detection of analog dial gauges, particularly in the energy and household sectors, but the problem is not yet sufficiently addressed in research. Our method is a universal three-level model that takes an image as an input and outputs circular bounding areas, object classes, grids of reference points for all symbols on the front panel of the device and positions of display pointers. Since all analog pointer meters have a common nature, this multi-cascade model can serve various types of devices if its capacity is sufficient. The model is using global regression for locations of symbols, which provides resilient results even for low image quality and overlapping symbols. In this work, we do not focus on the pointer location detection since it heavily depends on the shape of the pointer. We prepare training data and benchmark the algorithm with our own framework a3net, not relying on third-party neural network solutions. The experimental results demonstrate the versatility of the proposed methods, high accuracy, and resilience of reference points detection.
41
Ji, Zheng, Yifan Liao, Li Zheng, Liang Wu, Manzhu Yu, and Yanjie Feng. "An Assembled Detector Based on Geometrical Constraint for Power Component Recognition." Sensors 19, no. 16 (2019): 3517. http://dx.doi.org/10.3390/s19163517.
Full textAbstract:
The intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios.
42
Biffi, Leonardo Josoé, Edson Mitishita, Veraldo Liesenberg, et al. "ATSS Deep Learning-Based Approach to Detect Apple Fruits." Remote Sensing 13, no. 1 (2020): 54. http://dx.doi.org/10.3390/rs13010054.
Full textAbstract:
In recent years, many agriculture-related problems have been evaluated with the integration of artificial intelligence techniques and remote sensing systems. Specifically, in fruit detection problems, several recent works were developed using Deep Learning (DL) methods applied in images acquired in different acquisition levels. However, the increasing use of anti-hail plastic net cover in commercial orchards highlights the importance of terrestrial remote sensing systems. Apples are one of the most highly-challenging fruits to be detected in images, mainly because of the target occlusion problem occurrence. Additionally, the introduction of high-density apple tree orchards makes the identification of single fruits a real challenge. To support farmers to detect apple fruits efficiently, this paper presents an approach based on the Adaptive Training Sample Selection (ATSS) deep learning method applied to close-range and low-cost terrestrial RGB images. The correct identification supports apple production forecasting and gives local producers a better idea of forthcoming management practices. The main advantage of the ATSS method is that only the center point of the objects is labeled, which is much more practicable and realistic than bounding-box annotations in heavily dense fruit orchards. Additionally, we evaluated other object detection methods such as RetinaNet, Libra Regions with Convolutional Neural Network (R-CNN), Cascade R-CNN, Faster R-CNN, Feature Selective Anchor-Free (FSAF), and High-Resolution Network (HRNet). The study area is a highly-dense apple orchard consisting of Fuji Suprema apple fruits (Malus domestica Borkh) located in a smallholder farm in the state of Santa Catarina (southern Brazil). A total of 398 terrestrial images were taken nearly perpendicularly in front of the trees by a professional camera, assuring both a good vertical coverage of the apple trees in terms of heights and overlapping between picture frames. After, the high-resolution RGB images were divided into several patches for helping the detection of small and/or occluded apples. A total of 3119, 840, and 2010 patches were used for training, validation, and testing, respectively. Moreover, the proposed method’s generalization capability was assessed by applying simulated image corruptions to the test set images with different severity levels, including noise, blurs, weather, and digital processing. Experiments were also conducted by varying the bounding box size (80, 100, 120, 140, 160, and 180 pixels) in the image original for the proposed approach. Our results showed that the ATSS-based method slightly outperformed all other deep learning methods, between 2.4% and 0.3%. Also, we verified that the best result was obtained with a bounding box size of 160 × 160 pixels. The proposed method was robust regarding most of the corruption, except for snow, frost, and fog weather conditions. Finally, a benchmark of the reported dataset is also generated and publicly available.
43
Ramadhani, Moch Ilham, Agus Eko Minarno, and Eko Budi Cahyono. "Vehicle Classification using Haar Cascade Classifier Method in Traffic Surveillance System." Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, December 15, 2017, 57–64. http://dx.doi.org/10.22219/kinetik.v3i1.546.
Full textAbstract:
Object detection based on digital image processing on vehicles is very important for establishing monitoring system or as alternative method to collect statistic data to make efficient traffic engineering decision. A vehicle counter program based on traffic video feed for specific type of vehicle using Haar Cascade Classifier was made as the output of this research. Firstly, Haar-like feature was used to present visual shape of vehicle, and AdaBoost machine learning algorithm was also employed to make a strong classifier by combining specific classifier into a cascade filter to quickly remove background regions of an image. At the testing section, the output was tested over 8 realistic video data and achieved high accuracy. The result was set 1 as the biggest value for recall and precision, 0.986 as the average value for recall and 0.978 as the average value for precision.
44
Kyrychenko, Y. "FEATURES OF DEVELOPMENT A SYSTEM OF NUMBER PLATE LOCALIZATION BASED ON THE VIOLA-JONES METHOD USING ADABOOST." PARADIGM OF KNOWLEDGE 2, no. 28 (2018). http://dx.doi.org/10.26886/2520-7474.2(28)2018.3.
Full textAbstract:
The purpose of this work is to describe the method of the car number plate detection based on the Viola-Jones method using AdaBoost, and also to study the features of its work when changing the environmental conditions. As a result of the work, the task was formatted, the principles and method of its solution were formed, main features, problems and requirements for the training sample of this algorithm were described. After formulating the features of cascade training, a study was conducted to find out the measure of influence of certain external conditions on the detection of number plate by this method.Key words: detection of number plate, AdaBoost, Viola-Jones method, object detection.Кириченко Ю. В. Особенности построения системы локализации автомобильных номеров на основе метода Виолы-Джонса с использованием AdaBoost / Киевский политехнический институт им. Игоря Сикорского, Украина, Киев.Целью данной работы является описание метода выделения автомобильных номеров на основе метода Виолы-Джонса с использованием AdaBoost, а также исследование особенностей его работы при изменении условий окружающей среды от обучающей выборки. В результате проведенной работы была форматизирована задача, сформированы принципы и метод её решения, а также описаны основные особенности, проблемы и требования к обучающей выборке для данного алгоритма. После формулировки особенностей обучения каскада было проведено исследование для изучения степени влияния определенных внешних условий на поиск номера.Ключевые слова: выделение автомобильных номеров, AdaBoost, метод Виолы — Джонса, выделение объектов.Кириченко Ю. В. Особливості побудови системи локалізації автомобільних номерів на основі методу Віоли-Джонса з використанням AdaBoost / Київський політехнічний інститут ім. Ігоря Сікорського, Україна, Київ.Метою даної роботи є опис методу виділення автомобільних номерів на основі методу Віоли-Джонса з використанням AdaBoost, а також дослідження особливостей його роботи при зміні умов навколишнього середовища від навчальної вибірки. В результаті проведеної роботи було форматизовано завдання, сформований принципи і метод її вирішення, а також описані основні особливості, проблеми та вимоги до навчальної вибірки для даного алгоритму. Після формулювання особливостей навчання каскаду було проведено дослідження для вивчення ступеня впливу певних зовнішніх умов на пошук номера.Ключові слова: виділення автомобільних номерів, AdaBoost, метод Віоли-Джонса, виділення об'єктів.
45
Shamil, Haider, Bassam Al Kindy, and Amel H. Abbas. "Detection of Iris Localization in Facial Images Using Haar Cascade Circular Hough Transform." Journal of Southwest Jiaotong University 55, no. 4 (2020). http://dx.doi.org/10.35741/issn.0258-2724.55.4.5.
Full textAbstract:
In numerous science applications, face detection and iris extraction have been recognized as crucial stages by getting more consideration among researchers as it has an important job. This paper presents an automatic detection method of the iris and its center detection by applying the Haar Cascade Classifier and the Circular Hough Transform algorithm. The suggested method is divided into two primary methodologies: face recognition utilizes the Haar Cascade Classifier and iris extraction using the Hough Transform. The system detects the face from a set of facial images using an Impa-faced dataset. The improved AdaBoost algorithm constructs a cascaded classifier for face detection. Then, by applying the Haar Cascade to obtain an eye pair region and a Hough transform for iris detection by extracting Haar features. Finally, the improved circular Hough transform algorithm locates the iris center. The experimental results of the suggested method show a high-speed, robust ability to acquire the coordinates of the iris center accurately under various illumination changes on different states of human images. The overall accuracy for locating the iris center was 98.75%.
46
"Adaboost Cascade Classifier for Classification and Identification of Wild Animals using Movidius Neural Compute Stick." International Journal of Engineering and Advanced Technology 9, no. 1S3 (2019): 495–99. http://dx.doi.org/10.35940/ijeat.a1089.1291s319.
Full textAbstract:
Deep learning has gone deeper and has been utilized in almost all the applications like object recognition, image classification, speech recognition and much more. Most of the real-time applications rely on deep learning for accurate results. But one downside to the deep learning is its demand for GPUs (Graphical Processing Unit) or TPUs (Tensor Processing Units) for faster execution. There was no one-stop-shop hardware and software for deep learning applications, until recently Intel launched the Movidius Neural Compute Stick (NCS). This sleek device provides the power of GPU in a CPU based system. In this work, we have modeled an animal detection system using NCS and AdaBoost classifier powered by Multi-Block Local Binary Pattern (MB-LBP) features. The model has been built upon AlexNet and has achieved an average accuracy of 96.8% and a false rate 2.3% in classifying the animals as wild and non-wild. Furthermore, the model has a speedup of 467% when compared to the execution in the CPU based system.
47
Guan, Y. Q., H. S. Tan, F. Furtado, and A. Tan. "Application of Cascade Hand Detection for Touchless Interaction in Virtual Design." Journal of Computing and Information Science in Engineering 12, no. 1 (2011). http://dx.doi.org/10.1115/1.3615972.
Full textAbstract:
This paper proposes a method for robust hand detection for interactive touchless display using cascade classifier technique. A hardware system comprising a transparent display, two video cameras and a projector is assembled to generate on-display-surface object images for touchless display. A well-trained cascade of boosted classifiers is applied to detect the position of the hand in the object image. Using this method, accurate and robust hand detection for touchless display can be achieved. The detected hand trajectory information can be converted into mouse and keyboard inputs for interactive control and manipulation in virtual applications like virtual assembly and virtual design.
48
"Engrossing Prosecution of Code Smells Type Identification and Rectification using Machine Learning AdaBoost Classifier." International Journal of Innovative Technology and Exploring Engineering 9, no. 4 (2020): 624–31. http://dx.doi.org/10.35940/ijitee.d1331.029420.
Full textAbstract:
Software code smells are the structural features which reside in a software source code. Code smell detection is an established method to discover the problems in source code and reorganize the inner structure of object-oriented software for improving the quality of such software, particularly in terms of maintainability, reusability and cost minimization. The developer identified where the code smell is identified and rectified within a system is a major challenging issue. The various code smell detection technique has been designed but it failed to classify the code type and minimum rectification cost. In order to perform classification with minimum cost, an efficient technique called Machine Learning Ada-Boost Classifier (MLABC) technique is introduced. The MLABC technique improves the software quality by identifying and rectifying the different types of software code smell in source code. Initially, MLABC technique uses decision tree as base classifier to identify the code smell type. The decision tree is used to classify the code smell type based on the certain rule. After that, the base classifiers are combined to make a strong classifier using adaboost machine learning technique. The output of strong classifier is used to identify the code smell type. Finally, the code smell type rectification is performed by applying the refactoring technique where the code smell is identified with minimum cost and space complexity. Experimental results shows that the proposed MLABC technique improves the software code quality in terms of code smell type identification accuracy, false positive rate, code smell type rectification cost and space complexity with the source code
49
Chourasia, Khyati, and Jitendra N. Chourasia. "A Review and Comparative Analysis of Recent Advancements in Traffic Sign Detection and Recognition Techniques." SAMRIDDHI : A Journal of Physical Sciences, Engineering and Technology 2, no. 1 (2015). http://dx.doi.org/10.18090/samriddhi.v2i1.1594.
Full textAbstract:
This paper presents a comprehensive study of the automatic detection and recognition of traffic sign. The object of this review is to reduce the search for quality Traffic sign recognition system and to indicate the potential regions for increasing the efficiency, accuracy and speed of the system. The traffic sign carry the very important and valuable safety information through the peculiar characteristics. Different categories of traffic sign with their characteristics are presented. The practical difficulty that arises in actual time traffic sign is summarized. It describes also the techniques used for the detection, recognition and classification of the traffic signs. The traffic sign detection using color and shape detection are most commonly used. Some authors also used adaboost detector and decision tree method for detection. Most of the researcher used different type of Neural Network for recognition and classification. Some of the authors used fuzzy classifier and genetic algorithm. Template matching and model based method is also used for classification. A lot of improvements are still required for development efficient, fast, robustness traffic sign recognition system.
50
Chen, Guoqiang, Bingxin Bai, and Huailong Yi. "Pavement Pothole Detection Based on Cascade and Fusion Convolutional Neural Network Using 2D Images under Complex Pavement Conditions." Recent Patents on Engineering 14 (September 14, 2020). http://dx.doi.org/10.2174/1872212114999200914113515.
Full textAbstract:
Background: Background: The development of deep learning technology has promoted the industrial intelligence, and automatic driving vehicles have become a hot research direction. As to the problem that pavement potholes threaten the safety of automatic driving vehicles, the pothole detection under complex environment conditions is studied. Objective: The goal of the work is to propose a new model of pavement pothole detection based on convolutional neural network. The main contribution is that the Multi-level Feature Fusion Block and the Detector Cascading Block are designed and a series of detectors are cascaded together to improve the detection accuracy of the proposed model. Methods: A pothole detection model is designed based on the original object detection model. In the study, the Transfer Connection Block in the Object Detection Module is removed and the Multi-level Feature Fusion Block is redesigned. At the same time, a Detector Cascading Block with multi-step detection is designed. Detectors are connected directly to the feature map and cascaded. In addition, the structure skips the transformation step. Results: The proposed method can be used to detect potholes efficiently. The real-time and accuracy of the model are improved after adjusting the network parameters and redesigning the model structure. The maximum detection accuracy of the proposed model is 75.24%. Conclusion: The Multi-level Feature Fusion Block designed enhances the fusion of high and low layer feature information and is conducive to extracting a large amount of target information. The Detector Cascade Block is a detector with cascade structure, which can realize more accurate prediction of the object. In a word, the model designed has greatly improved the detection accuracy and speed, which lays a solid foundation for pavement pothole detection under complex environmental conditions.