To see the other types of publications on this topic, follow the link: Smoke Detector.
Dissertations / Theses on the topic 'Smoke Detector'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Smoke Detector.'
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 dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Goriachyi, P., and A. Demianenko. "Smoke detector." Thesis, Sumy State University, 2015. http://essuir.sumdu.edu.ua/handle/123456789/40483.
Full text
2
Geiman, Justin Aaron. "Evaluation of smoke detector response estimation methods." College Park, Md. : University of Maryland, 2003. http://hdl.handle.net/1903/113.
Full textAbstract:
Thesis (M.S.) -- University of Maryland, College Park, 2003.Thesis research directed by: Dept. of Fire Protection Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
3
Dawod, Jakob. "Seek : More than just a smoke detector." Thesis, Umeå universitet, Designhögskolan vid Umeå universitet, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-105986.
Full textAbstract:
Every year, approximately 100 people die in fire related incidents in Sweden. ”Seek” is designed to assist fire fighters to locate people faster in smoke diving procedures. ”Seek” identifies people and possible dangers within the building before the smoke diving procedure begins. This allows the operation to be streamlined and planned, as well as avoiding risks which fire fighters are exposed to today. The early overview created by the ”Seek” smoke detector not only saves time in planning but reduces the time from accident until the people in the burning building can receive skilled care, increasing their chance of survival.
4
Saunders, Julie Ann. "The Prediction of Smoke Detector Activation Times in a Two-Storey House Fire through CFD Modelling." Thesis, University of Canterbury. Civil and Natural Resources Engineering, 2010. http://hdl.handle.net/10092/4077.
Full textAbstract:
This report describes an investigation into the prediction of the activation times of domestic ionisation and photoelectric smoke detectors within a two storey dwelling, the work undertaken being an extension to that previously presented by Brammer (2002). Three fire scenarios are considered, each having been a real test fire undertaken at the Building Research Establishment in Cardington. These three fire scenarios all involved the flaming combustion of an upholstered armchair within the lounge on the Ground floor. During the experiments various results were recorded, including temperatures, optical densities and smoke detector activation times.
The fire scenarios where modelled using FDS, Version 5. Base parameters regarding the fuel load where defined to be 0.05kgsoot/kgfuel and 20MJ/kg. Consideration was also given to the effect varying the effective heat of combustion and defined soot yield would have on derived smoke detector activation times. Additional simulations where thus run considering soot yields of 0.04kgsoot/kgfuel and 0.10ksoot/kgfuel, and an effective heat of combustion of 25MJ/kg.
Three prediction methods where applied to the results of the FDS simulations for derivation of the activation times of smoke detectors located throughout the house. These methods where the temperature correlation method, Heskestad’s method, and Cleary’s method. The temperature correlation method considered activation criterions of 4°C, 13°C and 20°C above ambient.
The Heskestad and Cleary methods were found to derive comparable activation times for each detector location. None of the prediction algorithms where however found to predict activation times consistently comparable to the test data. Rather, it was determined that for an appropriate prediction method to be adopted for accurate assessment of a given fire scenario, consideration must be given to the:
• type of detector being assessed;
• location of the detector relative to the fire;
• mode of combustion (i.e. flaming or smouldering); and the
• growth rate of the fire.
5
Ierardi, James Arthur. "Characterizing the Entry Resistance of Smoke Detectors." Digital WPI, 2005. https://digitalcommons.wpi.edu/etd-dissertations/283.
Full textAbstract:
Entry resistance in smoke detectors was investigated using experimental and analytical approaches. The experimental work consisted of measuring velocity inside the sensing chamber of smoke detectors with a two-component Laser Doppler Velocimeter and exposing addressable smoke detectors to four different aerosol sources. The velocity measurements and exposure tests were performed in NIST's Fire Emulator / Detector Evaluator under steady state flow conditions in the range of 0.08 to 0.52 m/s. The addressable detectors were a photoelectric and an ionization detector. A specially constructed rectangular detector model was also used for the interior velocity measurements in order to have geometry compatible with numerical approaches, such as computational fluid dynamics modeling or a two-dimensional analytical solution. The experimental data was used to investigate the fluid mechanics and mass transport processes in the entry resistance problem. An inlet velocity boundary condition was developed for the smoke detectors evaluated in this study by relating the external velocity and detector geometry to the internal velocity by way of a resistance factor. Data from the exposure tests was then used to characterize the nature of aerosol entry lag and sensor response. The time to alarm for specific alarm points was determined in addition to performing an exponential curve fit to obtain a characteristic response time. A mass transport model for smoke detector response was developed and solved numerically. The mass transport model was used to simulate the response time data collected in the experimental portion of this study and was found, in general, to underestimate the measured response time by up to 20 seconds. However, in the context of wastebasket fire scenario the amount of underprediction in the model is 5 seconds or less which is within the typically polling interval time of 5 to 10 seconds for an addressable system. Therefore, the mass transport model results developed using this proposed engineering framework show promise and are within the expected uncertainty of practical fire protection engineering design situations.
6
Jankiewicz, Sean Phillip. "Predicting smoke detector response using a quantitative salt-water modeling technique." College Park, Md. : University of Maryland, 2004. http://hdl.handle.net/1903/1709.
Full textAbstract:
Thesis (M.S.) -- University of Maryland, College Park, 2004.Thesis research directed by: Dept. of Fire Protection Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
7
Goncharova, A. "Technology that makes our life easier." Thesis, Sumy State University, 2015. http://essuir.sumdu.edu.ua/handle/123456789/40482.
Full textAbstract:
Our present life is characterized by the increasing role of
technology, especially in everyday life. People make a fuss mainly
about technologies making their life easier and more convenient. It‘s
a social networking that really can be referred to one of them
8
Phelan, Patrick. "Investigation of enhanced soot deposition on smoke alarm horns." Link to electronic thesis, 2005. http://www.wpi.edu/Pubs/ETD/Available/etd-01075-121834/.
Full text
9
Lynch, James Andrew. "A study of smoke aging examining changes in smoke particulate size." Link to electronic thesis, 2004. http://www.wpi.edu/Pubs/ETD/Available/etd-0510104-194400/.
Full text
10
Wang, Ying, and Weiyi Lv. "Indoor video-based smoke detection." Thesis, Högskolan i Gävle, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-9573.
Full textAbstract:
Traditional smoke detection methods need sensors close to the source of the smoke. In order to avoid this disadvantage, this thesis presents a method for indoor video based smoke detection. In addition, it helps to improve the success rate of detection, as well as reducing the false detection rate of suspected smoke. This method consists of two parts. First, we create a Gaussian mixture model to detect smoke color pixels. Then, we use the smoke’s dynamic features to detect the smoke area and extract it from the area found in the first step, and in that way we can find the real smoke area. Our results show that this method can detect the smoke even before the flame appears. This will provide earlier warnings of fire, thus reducing economic losses and casualties.
11
Xie, Yong. "Detection of smoke and dust aerosols using multi-sensor satellite remote sensing measurements." Fairfax, VA : George Mason University, 2009. http://hdl.handle.net/1920/4595.
Full textAbstract:
Thesis (Ph.D.)--George Mason University, 2009.Vita: p. 136. Thesis director: John J. Qu. Submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Earth Systems and Geoinformation Sciences. Title from PDF t.p. (viewed Oct. 11, 2009). Includes bibliographical references (p. 126-135). Also issued in print.
12
Churches, David K. "The electromagnetic and acoustic properties of smoke particulates." Thesis, Open University, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.323122.
Full text
13
Singh, Rohitendra Kumar. "A study of air flow in a network of pipes used in aspirated smoke detectors." full-text, 2009. http://eprints.vu.edu.au/15172.
Full textAbstract:
Thesis (M. Eng.)--Victoria University (Melbourne, Vic.), 2009.Submitted in fulfilment of the requirements for the degree of Master of Engineering in Mechanical Engineering. Includes bibliographical references.
14
Huang, Yunyi. "Measuring flow in digital video containing smoke and gas." Thesis, Högskolan i Gävle, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:hig:diva-9528.
Full textAbstract:
Optical flow is widely used in image and video processing. This paper describes the definition of optical flow and some basic methods of estimating optical flow. There are three main optical flow methods described in this paper: Horn–Schunck method, Lucas–Kanade method and Anandan method. It will select the most appropriate method to measure the flow in videos containing smoke and gas by comparing those three methods with different criteria. The results are as below 1) Horn–Schunck method is good at measuring flow in infrared video and in horizontal direction, when 2) Anandan method is adept in estimating upward optical flow but not suitable for infrared video. 3) Lucas-Kanade method can be used not only in smoke videos, but also in methane gas videos, and it can detect flow in both horizontal and vertical direction.
15
Kouchinsky, Alan J. "Determination of smoke algoritm [i.e. algorithm] activation for video image detection." College Park, Md.: University of Maryland, 2007. http://hdl.handle.net/1903/7223.
Full textAbstract:
Thesis (M.S.) -- University of Maryland, College Park, 2007.Thesis research directed by: Dept of Fire Protection Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
16
Chen, L., W. Tang, N. W. John, Tao Ruan Wan, and J. J. Zhang. "De-smokeGCN: Generative Cooperative Networks for joint surgical smoke detection and removal." IEEE, 2019. http://hdl.handle.net/10454/17544.
Full textAbstract:
YesSurgical smoke removal algorithms can improve the quality of intra-operative imaging and reduce hazards in image-guided surgery, a highly desirable post-process for many clinical applications. These algorithms also enable effective computer vision tasks for future robotic surgery. In this paper, we present a new unsupervised learning framework for high-quality pixel-wise smoke detection and removal. One of the well recognized grand challenges in using convolutional neural networks (CNNs) for medical image processing is to obtain intra-operative medical imaging datasets for network training and validation, but availability and quality of these datasets are scarce. Our novel training framework does not require ground-truth image pairs. Instead, it learns purely from computer-generated simulation images. This approach opens up new avenues and bridges a substantial gap between conventional non-learning based methods and which requiring prior knowledge gained from extensive training datasets. Inspired by the Generative Adversarial Network (GAN), we have developed a novel generative-collaborative learning scheme that decomposes the de-smoke process into two separate tasks: smoke detection and smoke removal. The detection network is used as prior knowledge, and also as a loss function to maximize its support for training of the smoke removal network. Quantitative and qualitative studies show that the proposed training framework outperforms the state-of-the-art de-smoking approaches including the latest GAN framework (such as PIX2PIX). Although trained on synthetic images, experimental results on clinical images have proved the effectiveness of the proposed network for detecting and removing surgical smoke on both simulated and real-world laparoscopic images.
Research Development Fund Publication Prize Award winner, November 2019.
17
Maguire, Gabriel. "Remote Smoker Monitoring System Incorporating Preemptive Smoking Detection." Case Western Reserve University School of Graduate Studies / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=case1623268732185854.
Full text
18
Kohler, Daniel G. "STUDY OF STATISTICAL AND COMPUTATIONAL INTELLIGENCE METHODS OF DETECTING TEMPORAL SIGNATURE OF FOREST FIRE HEAT PLUME FROM SINGLE-BAND GROUND-BASED INFRARED VIDEO." DigitalCommons@CalPoly, 2012. https://digitalcommons.calpoly.edu/theses/796.
Full textAbstract:
This thesis will analyze video from land-based, cooled mid-wave infrared cameras to identify temporal features indicative of a heat plume from a forest fire. Desirable features and methods will show an ability to distinguish between heat plume movement and other movements, such as foliage, vehicles, humans, and birds in flight. Features will be constructed primarily using combinations of statistics and principal component analysis (PCA) with intent to detect key characteristics of fire and heat plume: persistence and growth. Several classification systems will combine and filter the features in an attempt to classify pixels as either heat or non-heat. The classification systems will be tuned and compared with common metrics of error rate and computation time. It was found that the movement pattern of a heat plume could be distinguished from the similar movement pattern of foliage by detecting outlier movement patterns, a phenomenon associated with the growth property of fire. Outlier movement patterns were best detected by thresholding the quotient of mean and median of a set of variance measurements over time. The best tested classifier in terms of minimizing false positives without losing the heat signal came from PCA of a dual-range moving average difference.
19
Alsaadi, Abdulrahman. "Smart smoke and fire detection with wireless and global system for mobile technology." Thesis, California State University, Long Beach, 2016. http://pqdtopen.proquest.com/#viewpdf?dispub=1606705.
Full textAbstract:
Fire safety is one of the major concerns for a safe home environment. Current implementations of home or workplace environment monitoring systems consist of rudimentary smoke detectors devoid of any communication capabilities. Recent trends in the industry have shown a growth in the use of smart devices at homes and with the recent advances in areas of machine learning and data sciences, this trend is expected to evolve at a rate faster than ever before. These smart devices constantly monitor the data of their environment and make decisions by performing data analytics on those observations. Amazon Echo is one such example where an ‘always-listening’ device responds intelligently to a speaker’s command giving its users a Smart Home experience.
In this implementation, we harness the developments in aforementioned areas to make Smart Fire Alarm System. The Smart Fire Alarm constantly monitors the environment and not only alerts the facility where it is located, but it also communicates with the fire department and the guardian of the property through Global System for Mobile (GSM) Communication making the damage control procedures efficient and faster. An ARM7 processor (LPDC 2148), ZigBee IEEE 802.15.4 protocol, and GSM subsystems are used in this implementation to communicate between the base station and smoke detectors.
20
Garges, David Casimir. "Early Forest Fire Detection via Principal Component Analysis of Spectral and Temporal Smoke Signature." DigitalCommons@CalPoly, 2015. https://digitalcommons.calpoly.edu/theses/1456.
Full textAbstract:
The goal of this study is to develop a smoke detecting algorithm using digital image processing techniques on multi-spectral (visible & infrared) video. By utilizing principal component analysis (PCA) followed by spatial filtering of principal component images the location of smoke can be accurately identified over a period of exposure time with a given frame capture rate. This result can be further analyzed with consideration of wind factor and fire detection range to determine if a fire is present within a scene. Infrared spectral data is shown to contribute little information concerning the smoke signature. Moreover, finalized processing techniques are focused on the blue spectral band as it is furthest away from the infrared spectral bands and because it experimentally yields the largest footprint in the processed principal component images in comparison to other spectral bands. A frame rate of .5 images/sec (1 image every 2 seconds) is determined to be the maximum such that temporal variance of smoke can be captured. The study also shows eigenvectors corresponding to the principal components that best represent smoke and are valuable indications of smoke temporal signature. Raw video data is taken through rigorous pre-processing schemes to align frames from respective spectral band both spatially and temporally. A multi-paradigm numerical computing program, MATLAB, is used to match the field of view across five spectral bands: Red, Green, Blue, Long-Wave Infrared, and Mid-Wave Infrared. Extracted frames are aligned temporally from key frames throughout the data capture. This alignment allows for more accurate digital processing for smoke signature. v Clustering analysis on RGB and HSV value systems reveal that color alone is not helpful to segment smoke. The feature values of trees and other false positives are shown to be too closely related to features of smoke for in solely one instance in time. A temporal principal component transform on the blue spectral band eliminates static false positives and emphasizes the temporal variance of moving smoke in images with higher order. A threshold adjustment is applied to a blurred blue principal component of non-unity principal component order and smoke results can be finalized using median filtering. These same processing techniques are applied to difference images as a more simple and traditional technique for identifying temporal variance and results are compared.
21
Bailey, Larissa Lynn. "Estimating detection probabilities for terrestrial salamanders in Great Smoky Mountains National Park." Connect to this title online, 2002. http://www.lib.ncsu.edu/theses/available/etd-08022002-111548/unrestricted/etd.pdf.
Full text
22
Brown, Kwame Agyapong. "Possible detection of pathogenic bacterial species inhabiting streams in Great Smoky Mountains National Park." Thesis, Western Carolina University, 2016. http://pqdtopen.proquest.com/#viewpdf?dispub=10244518.
Full textAbstract:
Numerous pathogenic bacterial species have been found in many freshwater systems around the world. These pathogens affect the overall water quality of these systems and may cause diseases in both aquatic and terrestrial animals which may lead to loss of species diversity and abundance in their environments. This study sought to identify and document pathogenic bacterial species that may inhabit the streams that flow through Great Smoky Mountains National Park. Bacterial cells were collected by filtering water from four streams (Oconaluftee River, Kephart Prong, Little Pigeon River and Hickory King Branch Stream) through separate capsule filters. The cells were later backflushed from the filters and cultured on various selective and differential media. Ten isolates were selected based on phenotypic characteristics such as colony color and growth on specific media type, and sample origin. The nearly full 16S rDNA was sequenced for all ten isolates and analyzed to determine their identity.
Out of the ten isolates, four isolates were from the phylum Firmicutes while the other six were in the phylum Proteobacteria. Phylogenetic analysis of these isolates showed eight out of the ten isolates were related to known opportunistic pathogens. The other two were related to a ubiquitous Bacillus species that is considered to be a probiotic. Although none of the isolates had a 100% match to a known obligate or opportunistic pathogen, many isolates matched > 97% to opportunistically pathogenic species. Follow up molecular and metabolic tests need to be employed to determine the pathogenicity of each isolate.
23
Ďuriš, Denis. "Detekce ohně a kouře z obrazového signálu." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-412968.
Full textAbstract:
This diploma thesis deals with the detection of fire and smoke from the image signal. The approach of this work uses a combination of convolutional and recurrent neural network. Machine learning models created in this work contain inception modules and blocks of long short-term memory. The research part describes selected models of machine learning used in solving the problem of fire detection in static and dynamic image data. As part of the solution, a data set containing videos and still images used to train the designed neural networks was created. The results of this approach are evaluated in conclusion.
24
Schneider, Dirk. "Untersuchung von Methoden zur Früherkennung von Bränden in Wald- und Vegetationsgebieten." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2017. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-227018.
Full textAbstract:
Dissertation of Chief Fire Officer Dipl.-Ing. M. Sc. Dirk Schneider for achieving the academic degree of Dr.-Ing. of the Faculty of Forestry, Geo and Hydro Sciences of the Technical University of Dresden with the title: “Early Detection of Fires in Areas of Forests and other Vegetation”
Fires threaten and destroy extensive forest and vegetation areas every year, endangering people and its settlements, leading to significant pressures on the environment and destroying considerable high value resources. The expenditures in manpower, logistics and finance for safety in general and fire suppression in particular are considerable. To minimize these varied and extensive consequences of fires, early detection is desirable, making an effective firefighting strategy possible. This early detection is particularly of importance in remote, large-scale areas and territories not under observation by the population, especially if they are subject to an increased or high vulnerability. After investigating and considering the causes, that repeatedly lead to forest fires not only in the Federal Republic of Germany but worldwide, the author describes different traditional and modern methods for early detection of fires in areas of forests and other vegetation. Furthermore the author develops a performance item catalog, basing on practical and economic experience, by which not only novel early warning systems can be developed, but the systems and methods described in the present study also are assessed and compared. The comparison of various early warning systems is guided not only by means of technical features, but also from an economic perspective. Financial calculation methods, staff costs and the peculiarities in public administration are particularly noted. The author also shows the different parameters that influence the selection of an appropriate early warning system for the detection of forest and vegetation areas. It becomes clear that it is the scene of the incident with its specific parameters that determines the most useful early warning system.
25
Hung, Ming-Mao, and 洪銘懋. "The sensitive analysis of photoelectrical smoke detector." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/bmqxvq.
Full textAbstract:
碩士國立交通大學
工學院產業安全與防災學程
102
Fire detector is a very reliable forewarning device; photoelectrical smoke detector is generally installed which concern the effectiveness for a given period of time. The effectiveness of period of time influence opportunity for locked people to escape. According to the Taiwan Fire Safety Equipment Approval Standard, smoke detector need to be installed in the vary type of locations, and one of this type- photoelectrical smoke detector is the priority option. However, the factors of the installed area are hard to control, such as, the wind speed, and the flow rate. For feature requested, most factories produced different type of features and appearance. Besides, in the current testing standard, the sensitivity tests of photoelectrical smoke detector was only on the actuating under standard concentration and limited time without the angle, direction, and vary flow rate consideration. However, if the factors consideration was ignored, false alarm caused easily which will decrease the available escape time. Therefore, flow rate and direction examination is a mainly subject for testing the sensitivity of photoelectrical smoke detector.
26
Kuo, Chen-Chang, and 郭振昌. "Patent Mapping and TRIZ Innovative Design of Smoke Detector." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/72c5kz.
Full textAbstract:
碩士國立臺北科技大學
電資碩士班
96
Fire often causes certain levels of losses and innumerable families breaking. The major goal of the essay is, with the present fire-alarm smoke detector that is in the mostly widespread use, making a full patent analysis and the TRIZ technique utilization to discover the appropriate way and to avoid the patent infringement. By means of this, we can create more innovative patents and enhance the profit ability for enterprises. On the one hand, it may save the research and development funds as well as prevent the potential disbursement in lawsuit owing to the patent infringement thereafter. In view of the numbers of the patents concerning the article “ smoke detector ” in cross-strait study, at present the development in mainland China is playing an active role in this domain even though nearly ten to fifteen years late. The analysis shows its development in growth and has been continually rising in the numbers of patents. On the contrary, in the aspect of the Republic of China (Taiwan), the manufacturers generally consider the fire equipment as a traditional industry. Most of the profession’s talents tend to work for the fields of semiconductor, and high-tech industry. As compared, it is easier to find the related talented persons in Mainland China rather than in the Republic of China (Taiwan). In addition, the Republic of China (Taiwan) is facing the crisis of price inflation due to petroleum rise in the recent years. Moreover, the human affairs cost and the material increase surged upward. All these make it hardly to compete with mainland China. The essay completed the patent analysis of the smoke detector. It provides the announcement of patent retrieval and analysis in the areas of Republic of China (Taiwan) and mainland China, and designs the patent map to make valuable suggestions. With the innovation of the TRIZ method, it will provide a model for the future establishment in Republic of China (Taiwan) for the way to avoid the patent infringement.
27
Chau-Yu, Gong, and 宮肇猷. "Apply Fire Dynamics Simulation to Assisted Apiration Smoke Detector Design." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/57433918366427179155.
Full textAbstract:
碩士中華大學
營建管理學系碩士班
100
Because of the complexity of modern architecture and large-scale fires, it may be accompanied by a huge property losses and personal injury or even death; building fire is an important issue for today's Social Security. If the particles for smoke detection, fire alarm ahead of time, early fire-fighting and evacuation operations, you can reduce the disaster, disaster, the loss tends to the minimum, so very early fire detection will be born out. In this study, using computational fluid dynamics(CFD), based on fire dynamics simulation software (FDS) assist Aspiration smoke detector (ASD) design of large high-ceilinged space with actual experimental data analysis, mutual authentication to provide more solutions for fire safety design. FDS is a tool to simulate two smoke source, smoke particles and oil; smoke particles, the purpose of acceptance testing, in accordance with the FIA testing standards and simulation of slow growth fire; oil to explore stratification effect.The simulation of fast-growing line of fire. And then simulated three kinds of air flow field wind speed.The study found that in the FDS simulation ASD design, simulation results and the actual time data close to actual experimental data but results approximate the actual data tends to be idealistic.If you use of FDS data simulation ASD system design, reference for analog data need to set aside a certain amount of flexibility.
28
LAI, MING-HUA, and 賴明華. "Research about the Correlations between Locating Smoke Detector and Responding Time." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/jj228j.
Full textAbstract:
碩士國立臺北科技大學
能源與冷凍空調工程系
107
Among all kinds of fire safety equipment, the fire alarm system plays an important leading role. The detection time of the fire detector is also a critical factor for escape and fire rescue. Various state-of-the-art interior designs have been adopted in modern buildings, one of which is the architectural and decorative ceilings are designed to be open beam ceilings type. For this kind of design concept, the location of the fire detectors should be installed in the ceiling or installed under the upper floor is not specifically defined in “Laws & Regulations of Fire”. This study will focus on the influence between fire detector installation location and fire response time. In this study we use 3D CFD software Fire Simulation Dynamics (FDS) to simulate the smoke flow inside the building and analyze the smoke propagation mode during fire. The simulation results will show the effect on the detector’s response time in the exposed-ceilings scenario space with different aperture ratios (10%, 20% and 30%).
29
Yeh, Shu-Tsun, and 葉書村. "The Effectiveness Evaluation of Aspiration Smoke Detector System in Non-Clean room Zone." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/45507840998075956156.
Full textAbstract:
碩士長榮大學
職業安全與衛生學系碩士在職專班
102
The science and technology industry not only provides country large volume of job creation but also as the main driving force for economy development. Thus any production shut down is not allowed, for the long term production shut down caused by fire will be worse impact. The social security, human resource allocation and international competition capability will be knocked down. All science and technology industry (such as semiconductor, panel industry. and etc.) been investing high volume manpower (for ERT training/ risk assessment…) and facilities (Fire fighting system, emergency communication system and etc.) to control fire situation in the beginning stage, it will reduce damage loss and protect people. The clean room is major production facilities installed, because the dust-free space with reliable production performance for semiconductor. The facilities including a lot of high value equipment such as ion implantation equipment, wet bench and etc., and these equipments apply various type of flammable gas during production. There were a lot of research in consider of economy value and protection risk to determine regulations and suggestions. The clean room has been with definite position for the Air sampling smoke detection system. But not for non-clean room area; most cases upon vendor suggestion for set up and not confirmed by research. The thesis is for this subject and research in a few set up cases related accident analysis expect to define the FMEA (failure mold evaluation analysis) for high/middle/low risk level. (Suggestion: Low risk no need to set up air sampling smoke detection system) The research provides optimized set up equipment with safety protection and cost saving. In order to achieve the maximum of efficiency, the Air sampling smoke detection system should focus on the total response time (Detect/ Confirm / Shut Off / Report) as a precondition. In accordance with various factors for discussion and correction such as the sampling pipe allocation / steps & routes of drill ... etc. The system not only detects any equipment burning in shortest time but also the device shut off immediately in chain reaction before power outage. We hope any producing interruption does not occur.
30
Huang, Yi-Chueh, and 黃亦爵. "Application of AHP and FAHP to Risk Assessment for Failure of Photoelectric Smoke Detector." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/4tec3u.
Full textAbstract:
碩士國立高雄應用科技大學
土木工程與防災科技研究所
105
Photoelectric smoke detector is one of the most popular fire alarm devices today, and its advantages are low cost, easy installation, fast reaction, etc. Photoelectric smoke detector is needed to follow “The rule of installing fire safety device at kinds of places. “ however, some detectors following the rule to install still have highly risk potential. The research conducts different analytical hierarchy processes (AHP) based risk analysis, considering three factors in top-layer: humans, devices, and the environment. In addition, nine influence factors in sub-layer are: outside injury or failure, the maintenance of point check not to be carried out, the machine vibration result in error message, electric contact not to be set up, the detector and line ageing, insufficient voltage, current temperature and humidity, the erosion of chemistry and acid and alkali. Then two fuzzy-based AHP and FAHP with triangular and trapezoidal membership functions, are employed. Relative risk impact (RRI) and then overall risk indices (ORI) can be calculated using AHP and two FAHPs. Three practical examples will be adopted for investigation. The research results prove that the risk analysis of AHP, FAHP (triangle), and FAHP (trapezoid) come to be correspondent. Comprehensive analysis of the results, “Environmental factors” under the “chemical acid and damage” is the impact of photoelectric smoke detectors failure of the biggest key factors. It depicts that when the customer install photoelectric smoke detectors, not only following rules to install but also no ignoring other factors could affect detection which contribute to decide whether the place is suitable to install or not. Thus, providing more guarantee for safety of human life and property in places.
31
Chen-YuTsai and 蔡承諭. "The Public Policy Promotion and Innovation Diffusion of Fire Department-Taking The Smoke Detector Fire Department of Tainan City Government Promote As Example." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/bgabqu.
Full textAbstract:
碩士國立成功大學
企業管理學系碩士在職專班
102
The smoke detector has been promoted by developed country like England, U.S. and Japan for couple of years. However, it is a novel and inexperienced fire safety equipment for our national. Relative fire authorities should raise people’s willingness installing smoke detectors by standard marketing methods, so that the penetration of smoke detectors could be elevated. Meanwhile, we can promote other safety policy at the same time to make people’s daily life more secure. This research is established based on innovation diffusion theory, public policy promotion, and technology acceptance model. For innovation diffusion theory, this research considers comparative advantage and compatibility as the main perceived factors of people with regard to novel things. For public policy promotion, we take policy promotion as products and services selling to complement the general knowledge of fire secure. The policy promotion factors we used are service, imforming/educating and personnal. We further import both innovation diffusion theory and public policy promotion into technology acceptance model in order to discuss the perceived usefulness and behavior intention of people using smoke detector. According to our research results, first of all, the comparative advantages and compatibility of user’s cognitive are with significant impact to perceived usefulness. Second, the profession and beneficial service, and the extent of mass communication are with significant impact to perceived usefulness. Third, the personnel’s effort of user’s cognitive are not with significant impact to perceived usefulness. Forth, perceived usefulness play a intervening variable during the effective process of relative advantage, compatibility, profession and beneficial service, and the extent of mass communication to behavior intention. In summary, this research has proved relative advantage, compatibility, profession and beneficial service, and the extent of mass communication are benefit to raise the percentage of people installing smoke detector. And personnel’s effort such like helping or teaching people to install smoke detector are not useful.
32
Huang, Jian-Wei, and 黃建瑋. "Intelligent Video-based Smoke Detection." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/38564911909343106983.
Full textAbstract:
碩士義守大學
資訊工程學系
102
In order to have a healthy living environment, smoking areas are often set up in certain places. However, a few people still like to smoke in public places with no-smoking signs and then many non-smokers have possible dangers of second-hand smoke. With the purpose of protecting the rights and interests of non-smokers, this thesis is focused on a real-time video surveillance system which is able to detect cigarette smoke through analyzing cigarette smoke color features from successive images taken by the surveillance cameras. In combination with the function of face detection to automatically identify smoking behavior, it is expected to judge whether there is any smoking behavior conducted in public places.
33
Lee, Chen-Yu, and 李鎮宇. "Spatio-Temporal Analysis in Smoke Detection." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/09571381441239206343.
Full textAbstract:
碩士國立交通大學
電機與控制工程系所
97
Visual-based smoke detection techniques in surveillance systems have been studied for years. However, given an image in open or large spaces with typical smoke and disturbances of commonly moving objects such as pedestrians or vehicles, robust and efficient smoke detection is still a challenging problem. In this paper, we present a novel and reliable framework for automatic smoke detection. Automatic monitoring systems use a stochastic approximation procedure, which is used to recursively estimate the parameters of the Gaussian mixture model and construct a background image for foreground segmentation. Next, spatial and temporal characteristics are analyzed of the candidate regions in the video sequences. It exploits three features: edge blurring, the gradual change of energy and the gradual change of chromatic configuration. In order to gain proper generalization ability with respect to sparse training samples, the three features are combined using a support vector machine based classifier. This system has been run more than 6 hours in various conditions to verify the reliability of fire safety in the real world. The results obtained from this novel approach would provide better insight to operators in the field of smoke detection to handle the problems of high false alarm rate and long reaction time.
34
洪肇廷. "Smoke Detection Based on Video Technology." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/85135253961938731119.
Full textAbstract:
博士國立交通大學
電控工程研究所
100
Smoke is an early sign of most fires; therefore, selecting an appropriate smoke-detection method is essential. Video-based fire detection is currently a fairly common application with the growth in the number of installed surveillance video systems. However, fast detecting smoke without creating a false alarm remains a challenging problem for open or large spaces with the disturbances of common moving objects, such as pedestrians and vehicles. Hence, two important targets for improving video-based smoke detector are the short reaction time and the low false alarm rate. This thesis aims to fast detect smoke while eliminate false alarm cases by analyzing features which is linearly separable. This thesis proposed three linear separable features and also introduces a framework for design a simple Video Technology-based system with temporal and spatial analysis. In this study, the process of extracting smoke features from candidate regions was accomplished by analyzing the spatial and temporal characteristics of video sequences for three important features: edge blurring, gradual energy changes, and gradual chromatic configuration changes. The proposed spatial-temporal analysis technique improves the feature extraction of gradual energy changes. Moreover, this thesis proposed a global verification stage based on the statistic of calculated local features to further lower the false alarm rate. The effectiveness of the proposed algorithm was evaluated on a PC with an Intel® Core™2 Duo CPU (2.2 GHz) and 2 GB RAM. The average processing time was 32.27 ms per frame, i.e., the proposed algorithm can process 30.98 frames per second. Experimental results showed that the proposed system can detect smoke effectively with a low false-alarm rate and a short reaction time in many real-world scenarios.
35
Chen, Chun-Yang, and 陳君暘. "Smoke Behavior Detection Based on Human Face." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/23460545253950027883.
Full textAbstract:
碩士真理大學
資訊工程學系碩士班
99
Since the implementation of Tobacco Hazards Prevention Act, the prohibition against smoking in public places tends to be stricter in Taiwan. Its emphasis level can be inferred from the frequent law amendments in recent years. In order to effectively improve the prevention effect and bring down the costs of human surveillance, this paper proposes a smoking behavior detection system based on the human face analysis, which can quickly and accurately detect whether the person in the image is smoking or not. First, the system makes use of the existing facial detection scheme to locate the mouth, and then conducts white balance processing on the detected face image so as to reduce the misjudgment caused by the light. It then implements color segmentation and noise elimination in HSV color system in order to determine the location of the cigarette. The range between the location and the mouth is used to determine whether the person is smoking or not. This study hopes to combine with the indoor monitoring system to automatically detect the illegal behavior and send out alarms to notify the responsible units for reference.
36
邱詩婷. "Smoke Detection Based on Image Visual Features." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/58102721530926483955.
Full textAbstract:
碩士國立交通大學
電控工程研究所
99
Vision is one of the most direct receptors. The current surveillance that is still a human equipped with video monitors. Highly homogeneous work like this, the human beings will be out of attentions and become poor efficiency. This paper will introduce an automatic monitor system to complete the associated mission. It will save on the cost and also have related work efficiently without an exhausted condition. There are lots of kinds of monitoring systems. This paper focuses on smoke detection. In this paper consists of "smoke features introduction", "Introduction to smoke detection algorithm" and "experimental results". About introduction, in order to adapt to different environments, our work focuses on the correlations of smog and background. Then design the rules to implement smoke detection systems. Analysis of experimental results, we design various experimental scenes, the natural environment, Muja tunnel, outdoor, indoor, and nighttime. We will take a look of the previous related research and analysis, and discuss the differences.
37
Cheng, Jiang-Chien, and 江建成. "Smoke Detection for Vehicles in Road Environment." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/30630024727151767671.
Full textAbstract:
碩士國立高雄應用科技大學
資訊工程系
100
In recent years,Smoke Detection for image has applied to intelligent surveillance system. How to catch the moving objects in the foreground and separate smoke from vehicles is a fresh and difficult issue for environment protection.In the study, a method that combined temporal-spatial and color information is used to select the features of moving object and then detects that the smoke exists in the image or not.First, histogram of statistic pixels is adopted for background rebuilding.An approach that combined temporal-spatial and angle-module to find moving objects.Color analysis reserves information matching smoke feature.Finally, sum of squared difference for optical flow processing is suggested to improve accuracy of smoke recognition.
38
Chung, Chi-Hung, and 張吉弘. "Video-based Fire and Smoke Detection System." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/06965426742936856902.
Full textAbstract:
碩士國立暨南國際大學
資訊工程學系
102
Along with the progress of computer technology, sophisticated image processing/understanding methods have developed and the application of intelligent video surveillance system are becoming more and more popular. In this thesis, we use image processing techniques to analyze image features of flame and smoke. The image features are then used to develop a video-based fire and smoke detection system. The proposed system consists of the fire detection module and the smoke detection module. In the fire detection module, we first detect foreground objects with a proper background model. Then, three pre-trained fire color look up tables, an LDA model, the standard deviation of the G-channel, an evaluated flame risk value are used to detect flame in video. In the smoke detection module, we use dark channel analysis to extract suspicious blurry regions from video. Also, we use wavelet analysis to determine whether the high frequency image energy is reducing. Then, smoke candidate regions are computed and are tracked to examine if the area of any of them keeps growing. When the area of a smoke candidate is increasing, it is determined to be a smoke region. Experimental results show that, when the input video resolution is 640×480, the fire and smoke detection speed is 100 frames/sec., and the recognition accuracy is about 92%.
39
Peng, Shen-Chieh, and 彭聖傑. "Smoke Detection Using Global and Local Features." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/35942372244330965413.
Full textAbstract:
碩士國立交通大學
生醫工程研究所
99
This study presents a novel smoke detection approach using local feature analysis and global feature verification. Studies have investigated visual-based smoke detection techniques in surveillance systems for years. However, given an image in open or large spaces with typical smoke and disturbances of commonly moving objects such as pedestrians or vehicles, detecting smoke without false alarm is still a challenging problem. It is important to find features to distinguish smoke from various environments. This study analyzes characteristics of candidate blocks in video sequences to exploit local features: edge blurring, gradual energy change and gradual color configuration change. Each local feature is strong enough to detect smoke with few false alarms. Moreover, proposed features are complementary to each other. Hence, local features are combined to lower the false alarm rates by boosting cascade architecture. To further overcome some false situation, global feature verification is proposed to gather statistics of information on contour and in the whole area of each candidate region. Experimental results show that the proposed system can well detect smoke with low false alarm rate within a short reaction time in various environments. The whole system can run in real time and has been implemented on embedded system.
40
Tai, Wen-sheng, and 戴文聖. "The Analysis of Smoke Detection on Performance of Smoke Exhaust System in Buildings with Atrium." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/68796057030139896442.
Full textAbstract:
碩士國立中山大學
機械與機電工程學系研究所
93
Recently, plenty of large/public buildings have been completed in Taiwan. For bright indoor environment and comfortable feelings, these buildings often utilized lots of large spaces such as atria. However, it is difficult to maintain tenable conditions within atria and large spaces in case of fire. Therefore, the alert of smoke detectors and the efficiency of smoke control systems are both very important when a fire occurred and people needed to evacuate. In large space buildings, the smoke exhaust fan and smoke storage are major design concepts of the passive smoke management systems in order to maintain tenable conditions in means of egress. In this research, the operation strategies of passive smoke management and fire detection systems in large space buildings will be systematically analyzed. The full-scale hot smoke test can be performed to evaluate the temperature distribution of smoke layer and the smoke descending rate at ABRI large space fire lab in Tainan. In the other hand, the beam detectors can not only detect smoke layer by fire more earlier but show excellent smoke rejection if they can be effectually connected with passive smoke control systems. It is anticipated that through the execution of this research project, the concept developed in this study can be applied to improve the passive smoke management performance of large space buildings in Taiwan.
41
Wu, Jin-Rong, and 吳晉榮. "Wavelet Based Fire and Smoke Detection In Video." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/13941578222494412004.
Full textAbstract:
碩士義守大學
資訊工程學系碩士班
98
In order to detect fire and smoke in the open space, this paper integration the same properties of the flame and smoke to detect whether an open space in the presence of fire and smoke. First, detection image if there are moving objects, then use the color of flame and the chrominance value change in background image caused by smoke to analysis the move region. The third and fourth step are used the frequency to analysis the boundaries and flicker or oscillations in a pixel due to fire and smoke. The last step is using the boundaries properties of fire and smoke to reduce the false positives. Final combined the results of all steps to determine whether the video presence fire and smoke. Because of using the above methods to detect fire and smoke will cause the false alarm rate is too high, at the end of this paper suggested several ways to improve the false alarm rate. Including improve the threshold of moving objects detection method and improve the time frequency identification methods and using the different methods to determine the contours of smoke.
42
Lin, Pa-Hsun, and 林伯勳. "Fire and Smoke Detection Using Random Forest Algorithm." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/56813956821976269774.
Full textAbstract:
碩士國立暨南國際大學
資訊工程學系
101
Along with the progress of computer computation capabilities, sophisticated image processing/understanding methods have been developed and the functions of intelligent video surveillance systems have been greatly extended. In this thesis, we develop a video-based fire and smoke detection system based on the random forest algorithm. We use the distinct color and image variation properties of fire/smoke to select candidate regions. Then, image features of texture and motion patterns of the candidate regions are analyzed to determine any fire/smoke region. We propose to extract the features of both the texture and motion patterns of the fire/smoke with the local binary pattern (LBP) method. The random forest method is augmented to use the LBP features for fire/smoke detection to reduce false positive and enhance the fire and smoke detection rate.
43
Yu, Ren-Min, and 郁仁民. "The Smoke Detection Algorithm Using Target Tracking in Video." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/16457517695100335387.
Full textAbstract:
碩士義守大學
資訊工程學系碩士班
99
In order to detect fire accident in the open space, the method is used by detecting smoke in the video. In this thesis, target tracking method and the properties analysis of smoke are used to confirm whether there is smoke in the video. First, moving objects in video are detected by using Gaussian Mixture Model algorithm, then labeling disconnected areas as different parts. After labeling, the location of current image components and previous image components are compared to confirm whether the same components, then the smoke features of each component are extracted separately and estimate the motion orientation. In smoke feature extraction, the chrominance of the component is checked and the component will be marked if it fits the condition. In motion orientation estimation, time and cost are saved by using integral image. Moreover, by calculating UMR (Upward Motion Ratio) the components of non-smoke motion like will be excluded. Finally, the results of all steps are combined to confirm whether smoke presences in the video. According to the experiment, thirteen videos that have different complexity background were used, and the smoke detection rate was 92%, while in the false positive rate was only 7%. Compared to the program results of based on wavelet transform, the method in this thesis has greatly reduced the false positive rate and the interference caused by non-smoke objects in video.
44
Yuan, Sou-Wei, and 袁守威. "Image-based Smoke Detection by Using Optical Flow Method." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/32990669373142349199.
Full textAbstract:
碩士國立交通大學
電機與控制工程系所
92
In recent year, digital video record system(DVR) is widely applied to various kinds of surveillance environment. Because of the advantage of digitization, a lot of image processing technology can be imbedded and combined together. In this thesis, study on a new method of smoke detection based on RGB color model mainly. At first, using a mould that represents with RGB model parameters separates out the smoke from the image and according to the characteristic that smoke moves upward. Utilize optical flow method to know the sport situation within the smoke and cooperate with the growth of smoke. Finally, fuzzy inference system judge the moving object is smoke or not. Then offer alarm information in right time. The proposed method is completely different to traditional smoke detector. This will have an opportunity to be applied on the outdoor space to prevent the emergence of the forest fire in the future. From the experiment results, if the area of appearing of the moving object is large enough, we can get satisfied result.
45
Chan, Po-Shan, and 詹博善. "Image Block Processing and Translucence for Video Smoke Detection." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/63307181192960774356.
Full textAbstract:
碩士國立成功大學
機械工程學系專班
97
Conventional fire detectors must contact these targets（heat or smoke） for being activated and, consequently, respond slowly. Video smoke detection has many advantages over traditional methods, such as fast response and non-contact, large space surveillance, and so on. But most of current methods for video smoke detection systems usually have high false alarms. By analyzing the characteristics of smoke motion, base on blocking image, a motion accumulation and translucence combined model is proposed for video smoke detection. Because smoke often emerges continually from the place of smoldering, an accumulation model is presented to extract these temporal-spatial visual features of early fire over a time window. The model synthesizes blocking image substrate method can mostly suppress noise. Smoke can blur colors of objects and partially obscure the object of background. After observing the phenomena, a translucence model is presented base on the RGB color space analysis of the moving block. Analysis the difference of the RGB increases intensity. And the model efficiently represents translucence of the smoke. Experiments show that the combined accumulation and translucence model is robust and significant for the smoke detection.
46
Photo-e, The Evaluation of Availability of Type Two, and 吳聰敏. "The Evaluation of Availability of Type Two Photo-electrical Smoke Detectors." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/n7v7ff.
Full textAbstract:
碩士長榮大學
職業安全與衛生學系碩士班
98
Fire detectors are very important devices in automatic detection systems. It is not appropriate to evaluate the availability of detectors by their smoke actuation time in smoke standard test. The actuation time of standard test is 60seconds for type two, but 20 seconds was found the better criteria for this type of detectors. Smoke actuation test and sensitivity test are always used to evaluate the availability of smoke detectors. The sensitivity of smoke detectors all fit in the required range of sensitivity test for different ages of detectors, so this test cannot be applied to judge the availability of used detectors. A detector, which smoke actuation time is 3 seconds, is judged as a failure detector in a smoke actuation test. The detector should be replaced to avoid the false-alarm in the future when its smoke actuation time less than 3 seconds in the smoke actuation test. The detector can be judged in a good condition when its actuation time is between 4 seconds and 20 seconds for type two smoke detectors in smoke actuation test. This result can be used as the standard for replacing the used detectors in smoke actuation test based on the requirement of smoke detection in fire code.
47
Kuan-ChenLiu and 劉冠成. "Smoke and Flame Detection Using Motion Information and Color Histogram." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/32303650600337086238.
Full text
48
Chiang, Pei-Yun, and 江珮筠. "Vision-based Fire and Smoke Detection with Spatial-Temporal Features." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/99909203978978345439.
Full textAbstract:
碩士中華大學
資訊工程學系碩士班
100
Conventional smoke and fire alarms are detected with the smoke and temperature sensors when the smoke and fire have occurred for a time period. Vision-based smoke and fire detection systems can detect the smoke and fire in time. In this study, a novel vision-based fire and smoke detection method is proposed to reduce the false alarm ratio significantly. Recently, vision-based studies applied visual features such as the color, motion, edges, and shape to detect the smoke and fire. However, vision-based detection methods will encounter the problems of the variations of illumination and color. Our proposed method integrates the features of scene change detection, color information, spatial-temporal analysis, and optical flow to detect the fire and smoke simultaneously. First, scene change regions are identified by the background subtraction and then the candidate flame regions are identified by applying fire-colord GMM models. Second, the temporal and spatial wavelet analyses are used to extract the motion and spatial texture distribution characteristics for the fire/smoke regions. Here, all the above-mentioned visual features are integrated with a rule-based judge rule to detect the occurrences of the fire and smoke in time. Finally, we utilize the optical flow features associated with the SVM classifier to verify whether the detected flame/smoke is valid or not. Experimental results show that the recognition rate can approach 98.0% with the efficiency 12 fps.
49
Yang, Tsung-Ju, and 楊宗儒. "Smoke Detection and Analysis of Ship Images in Keelung Harbor." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/kjhr7y.
Full textAbstract:
碩士國立臺灣海洋大學
海洋環境資訊系
106
In recent years, Keelung Harbor has gradually transformed into a tourist port, and aims to become the Taiwan's cruise home port. The cruises entered Keelung Harbor nearly 190 times in 2015, 222 times in 2016, 269 times in 2017, respectively. The docking area of the cruises is adjacent to the downtown, where is also the portal of Keelung. Therefore, to control the smoke exhaust of the ship, it is expected to establish the automatic detection by analyzing the image data. In the previous research, the detection of ship smoke was based on the analysis of visible (red, green, and blue) bands. In this study, in addition to visible band, the thermal infrared is used to capture images and the data of temperature variation are also included for detection and analysis of ship smoke images of Keelung Harbor. Firstly, the software, ENVI is used to analyze the multi-spectral image data composed of six bands (Red, Green, Blue, Temperature, Temperature gradient and Red gradient). Through the supervised classification method, the results of agreement show that 11 images are almost perfect, 12 images are substantial, 9 images are moderate, and 2 images are fair. Through the analysis of unsupervised K-means classification method and the validation of the region of interest, the results of agreement show that 8 images are substantial, and 26 images are almost perfect, but some of the images are disturbed by striped signals, which reduce the accuracy. The result shows that the automatic detection algorithm is available to detect the black smoke and exclude the grayer smoke. Twelve images in this study are the black-smoke, and twenty-two are gray-smoke ones. The automatic detection algorithm can exactly detect the black smoke images and the accuracy rate is 100%. Nevertheless, three gray images are still misjudged as black smoke, so its accuracy is 86.36%. Keywords: Ship smoke, Keelung Harbor, Image analysis, Infrared, Automated smoke detection
50
Yin, Yen-Hui, and 尹燕輝. "The Smoke Detection for Earily Fire-Alarming Based on Video Processing." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/67112921921817003664.
Full textAbstract:
碩士國立高雄應用科技大學
電子與資訊工程研究所碩士班
95
The paper presents a smoke-detection method for early fire-alarming system based on video processing. Real-time fire accident alarm rising is important, especially for the early time. Because the alarm is the more it sent out early, the more it can earn the time for people to take the emergency procedure and protect the security of the lives and properties. In general, most of combustible objects will generate smoke before it catches fire. So if we can early and correctly detect the smoke, it should be able to offer the early fire alarm. From the video image that We are captured by DVR, we extract the smoke-pixels to monitor and judge. The basic strategy of smoke-pixel judgment is composed of two decision functions: one is a chromaticity-based decision function in static characteristic and the other is a smoke source unchangeable and a diffusion-based decision function in dynamic characteristic. The chromatic decision rule is deduced by grayish color of smoke and the dynamic decision rule is dependent on The smoke produced from the source successively and the diffusion attribute of smoke. To give an appropriate alarm, a fuzzy scheme is introduced to enhance the reliability of alarming by checking if the quantity of smoke extracted increases with the checking time. Experimental results show that the proposed method can provide an early alarm at a lower false alarm rate before the fire burns up. Now, the digital monitoring system has been very general already. The application is sure to be more popular in the future. The proposed method can provide a reliable and cost-effective solution for smoke detection and hence is very attractive for the important places, social security, commercial applications, and so on.