【摘要】：火災(zāi)是嚴(yán)重威脅大類生產(chǎn)和生活安全的因素之一,通過火災(zāi)探測報警系統(tǒng)預(yù)防火災(zāi)對于保障人民的生命財(cái)產(chǎn)安全、維持社會穩(wěn)定具有重要意義。目前廣泛應(yīng)用的常規(guī)感煙、感溫火災(zāi)探測器多利用接觸式感知技術(shù),在應(yīng)用場所(空間、時間等)具有一定的局限性,不適用于層高較高的建筑及開放空間中的火災(zāi)探測,具有非接觸、響應(yīng)迅速、探測范圍大、主動可視等優(yōu)點(diǎn)的視頻火災(zāi)探測技術(shù)應(yīng)運(yùn)而生,被應(yīng)用于地面建筑、廠區(qū)、森林等場所的火災(zāi)監(jiān)測。目前的視頻火災(zāi)探測技術(shù)主要集中在視頻火焰探測、紅外探測等方面,而在及時性方面有更大優(yōu)勢的視頻煙霧探測技術(shù)在理論、方法和應(yīng)用上還存在很多問題亟待解決,如缺乏標(biāo)準(zhǔn)測試視頻庫、未對疑似煙霧區(qū)域提取方法進(jìn)行深入研究、在進(jìn)行相似運(yùn)動目標(biāo)分類方面缺乏有效特征、煙霧探測誤報率高等。本文旨在深入研究早期火災(zāi)煙霧視頻探測理論和方法,為視頻火災(zāi)探測技術(shù)的發(fā)展及應(yīng)用提供理論和技術(shù)支撐。本文在中國科學(xué)技術(shù)大學(xué)火災(zāi)科學(xué)國家重點(diǎn)實(shí)驗(yàn)室的標(biāo)準(zhǔn)試驗(yàn)間和低壓實(shí)驗(yàn)艙中設(shè)計(jì)搭建視頻拍攝系統(tǒng),獲取陰燃煙霧視頻圖像序列,進(jìn)行陰燃煙霧的視頻分割、特征提取和分析、特征識別等方面的研究,進(jìn)而設(shè)計(jì)完整的視頻火災(zāi)探測系統(tǒng),并對系統(tǒng)在低氣壓環(huán)境中應(yīng)用的可行性進(jìn)行實(shí)驗(yàn)驗(yàn)證。具體研究工作如下：(1)建立陰燃煙霧視頻基礎(chǔ)數(shù)據(jù)庫�；馂�(zāi)煙霧標(biāo)準(zhǔn)視頻圖像數(shù)據(jù)庫是研究視頻火災(zāi)煙霧探測原理、發(fā)展煙霧識別方法的原始數(shù)據(jù)基礎(chǔ)。在中科大火災(zāi)實(shí)驗(yàn)室的標(biāo)準(zhǔn)試驗(yàn)間和低壓實(shí)驗(yàn)艙內(nèi)搭建火災(zāi)陰燃煙霧視頻采集平臺,采用木材和棉繩作為實(shí)驗(yàn)材料產(chǎn)生陰燃煙霧,使用高清攝像機(jī)、紅外攝像機(jī)、高速攝像機(jī)等設(shè)備進(jìn)行煙霧視頻采集,對采集的視頻進(jìn)行標(biāo)準(zhǔn)化處理,最終建立陰燃煙霧視頻基礎(chǔ)數(shù)據(jù)庫。(2)提出并完成基于顯著性檢測的早期煙霧疑似區(qū)域分割方法。根據(jù)人眼視覺注意機(jī)制,陰燃煙霧可被看作是視頻中湍流和灰色顯著的區(qū)域,基于結(jié)合自頂向下和自底向上的視覺注意模型利用顯著性檢測方法進(jìn)行疑似煙霧區(qū)域分割。首先使用非線性增強(qiáng)方法對視頻的亮度圖像和光流圖譜進(jìn)行增強(qiáng),用增強(qiáng)后的圖像計(jì)算顯著性譜,然后用高斯混合模型(GMM)計(jì)算出的運(yùn)動前景構(gòu)造運(yùn)動能量函數(shù),對顯著性譜進(jìn)行估計(jì),分割出疑似煙霧區(qū)域。對幾種常用的傳統(tǒng)煙霧區(qū)域檢測方法的對比實(shí)驗(yàn)結(jié)果表明該方法具有更好的分割效果,并且計(jì)算速度也能夠滿足實(shí)時視頻煙霧探測的需求。(3)發(fā)展基于煙霧時空特征和檢測前跟蹤方法的視頻煙霧探測算法。為提高探測算法的準(zhǔn)確率和魯棒性,對每個候選煙霧區(qū)域進(jìn)行跟蹤,在一個時間窗口內(nèi)綜合空域和時域特征信息進(jìn)行火災(zāi)識別。通過對煙霧形成的物理過程和煙霧組分的分析,提出能夠描述湍流煙霧紋理的熵和對比度特征,并通過實(shí)驗(yàn)進(jìn)行特征有效性驗(yàn)證。結(jié)合陰燃煙霧圖像的紋理時空特征、顏色特征和速度特征,訓(xùn)練支持向量機(jī)分類模型,通過一個時間窗的多次分類結(jié)果的累積估計(jì)發(fā)生火災(zāi)的可能性。使用包含煙霧和非煙霧的視頻對算法性能進(jìn)行測試驗(yàn)證。實(shí)驗(yàn)結(jié)果表明該算法框架合理有效,而且通過修改框架中的組件,還可以快速完成火焰探測等其他功能。最后還對煙霧濃度對視頻煙霧探測的影響進(jìn)行實(shí)驗(yàn)分析,并指出煙霧濃度是火災(zāi)探測研究和工業(yè)應(yīng)用中需要考慮的重要因素。(4)設(shè)計(jì)陰燃煙霧視頻探測系統(tǒng),并對系統(tǒng)在低氣壓環(huán)境下的適用性進(jìn)行測試。根據(jù)實(shí)驗(yàn)結(jié)果和前期研究的視頻煙霧探測方法發(fā)展出視頻煙霧探測系統(tǒng)。用基于顯著性檢測的陰燃煙霧分割方法和檢測前跟蹤算法對不同氣壓下的煙霧視頻進(jìn)行分析,對不同氣壓下的陰燃煙霧區(qū)域進(jìn)行分割,提取煙霧區(qū)域特征,然后對視頻中煙霧區(qū)域的亮度、速度均值及方差、紋理的熵及對比度等特征進(jìn)行統(tǒng)計(jì)分析,并使用這些特征在不同氣壓下使用多種分類器進(jìn)行分類測試,實(shí)驗(yàn)研究結(jié)果表明本文提出的方法和特征在低壓環(huán)境下仍然適用。
[Abstract]:Fire is one of the factors that seriously threaten the production and life safety of the major categories. The fire detection and alarm system is of great significance to protect the life and property of the people and to maintain social stability. The conventional smoke-sensing and temperature-sensing fire detector which is widely used at present has a certain limitation in the application places (space, time, etc.), and is not suitable for fire detection in high-story buildings and open spaces, has non-contact and rapid response, Video fire detection technology, which has the advantages of large detection range, active visual and other advantages, comes into being, and is applied to the fire monitoring of the ground building, the plant area, the forest and other places. The current video fire detection technology mainly focuses on the aspects of video flame detection, infrared detection and the like, and the video smoke detection technology with greater advantages in the timeliness has many problems to be solved in theory, method and application, such as the lack of standard test video library, The method for extracting the suspected smoke area is not in-depth study, and there is a lack of effective characteristics in the classification of similar moving targets, and the smoke detection is false and high. The purpose of this paper is to study the theory and method of early fire smoke detection and provide theoretical and technical support for the development and application of video fire detection technology. In this paper, a video shooting system is designed in the standard test room and the low-pressure laboratory of the fire science national key laboratory in China's science and technology university, and the video image sequence of the smoldering smoke is obtained, the video segmentation, feature extraction and analysis of the smoldering smoke are carried out, the feature recognition and the like are carried out, And then a complete video fire detection system is designed, and the feasibility of the application of the system in the low-pressure environment is experimentally verified. The specific research work is as follows: (1) Create a negative-burning smoke video base database. The fire smoke standard video image database is the raw data base of the research on the principle of video fire smoke detection and the development of the smoke identification method. in that standard test room and the low-pressure experiment cabin of the middle and large fire laboratory, a fire-smoldering smoke video acquisition platform is built, wood and cotton ropes are used as experimental materials to generate smoldering smoke, and the smoke video acquisition is carried out by using a high-definition camera, an infrared camera, a high-speed camera and the like, The collected video is standardized, and a negative-burning smoke video base database is finally established. (2) An early smoke suspected area segmentation method based on saliency detection was proposed and completed. In light of that visual attention mechanism of the human eye, the smoldering smoke can be regarded as a region of turbulence and gray in the video, and the suspected smoke region is divide by a saliency detection method based on a visual attention model combined with the top-down and the bottom-up. firstly, the brightness image and the optical flow pattern of the video are enhanced by using a non-linear enhancement method, the saliency spectrum is calculated by the enhanced image, and then the energy function of the motion foreground tectonic movement calculated by the Gaussian mixture model (GMM) is used to estimate the significance spectrum, The suspected smoke area is divided. The experimental results show that the method has better segmentation effect and can meet the demand of real-time video smoke detection. And (3) developing a video smoke detection algorithm based on the smoke-time characteristic of the smoke and the tracking method before the detection. In order to improve the accuracy and the robustness of the detection algorithm, each candidate smoke area is tracked, and the air space and time domain characteristic information are integrated in a time window for fire identification. The entropy and contrast characteristics of the turbulence smoke texture can be described by the analysis of the physical process and the smoke component of the smoke formation, and the characteristic validity verification is carried out by the experiment. The probability of fire is estimated by the cumulative estimation of multiple classification results of a time window in combination with the texture space-time characteristics, the color characteristics and the speed characteristics of the smoldering smoke image, the training support vector machine classification model. The algorithm performance is tested and verified using video containing smoke and non-smoke. The experimental results show that the framework is reasonable and effective, and other functions such as flame detection can be accomplished quickly by modifying the components in the frame. Finally, the influence of the smoke concentration on the detection of the video smoke is analyzed, and the smoke concentration is an important factor that needs to be considered in the research of fire detection and industrial application. And (4) designing a smoldering smoke video detection system and testing the applicability of the system under the low pressure environment. And the video smoke detection system is developed according to the experimental results and the video smoke detection method of the earlier research. the smoke video under different air pressure is analyzed by using a negative-burning smoke segmentation method based on the significance detection and a detection front tracking algorithm, the smoke area of the smoldering smoke under different air pressure is divided, the smoke area characteristic is extracted, and then the brightness, the speed mean value and the variance of the smoke area in the video are extracted, The characteristics of the entropy and contrast of the texture are analyzed and tested by using a variety of classifiers under different air pressure. The experimental results show that the proposed method and features are still applicable in the low-pressure environment.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：X924.3;X932

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 程曉舫,王瑞芳,張維農(nóng),王亞雄;火災(zāi)探測的原理和方法(上)[J];中國安全科學(xué)學(xué)報;1999年01期

2 程曉舫,王瑞芳,張維農(nóng),王亞雄;火災(zāi)探測的原理和方法(下)[J];中國安全科學(xué)學(xué)報;1999年02期

3 潘剛;火災(zāi)探測報警技術(shù)發(fā)展趨勢[J];消防科學(xué)與技術(shù);2002年01期

4 陳啟元;淺談火災(zāi)探測報警產(chǎn)品在選擇使用中容易出現(xiàn)的誤區(qū)[J];山東消防;2003年05期

5 潘剛,馬騮;火災(zāi)探測傳感信息提取方法的研究[J];消防技術(shù)與產(chǎn)品信息;2004年03期

6 邱祥,高宇;高大空間火災(zāi)探測及滅火新技術(shù)的應(yīng)用前景[J];房材與應(yīng)用;2004年05期

7 翁立堅(jiān),宋立巍;一種關(guān)于點(diǎn)型探測器火災(zāi)探測能力的評估方法[J];火災(zāi)科學(xué);2005年02期

8 王麗萍;方厚輝;李亨;;基于多傳感器融合技術(shù)的高大空間火災(zāi)探測[J];科學(xué)技術(shù)與工程;2006年01期

9 王曄;;火車站極早期報警和可靠火災(zāi)探測[J];消防技術(shù)與產(chǎn)品信息;2007年02期

10 董文輝;王卓甫;梅志斌;厲劍;;火災(zāi)探測綜合評估試驗(yàn)臺測控系統(tǒng)集成[J];建筑電氣;2007年04期

相關(guān)會議論文 前10條

1 范雪成;;智能技術(shù)在火災(zāi)探測領(lǐng)域的發(fā)展趨勢[A];河南省土木建筑學(xué)會2008年學(xué)術(shù)交流會論文集[C];2008年

2 王樂天;王際錦;陳忠信;;智能技術(shù)在火災(zāi)探測領(lǐng)域的應(yīng)用[A];中國消防協(xié)會年會面向新世紀(jì)消防學(xué)術(shù)研討會論文集[C];1999年

3 丁宏軍;趙英然;;談火災(zāi)探測報警產(chǎn)品的設(shè)計(jì)生產(chǎn)和使用中存在的誤區(qū)[A];中國消防協(xié)會年會面向新世紀(jì)消防學(xué)術(shù)研討會論文集[C];1999年

4 潘剛;;火災(zāi)探測報警技術(shù)發(fā)展趨勢[A];展望新世紀(jì)消防學(xué)術(shù)研討會論文集[C];2001年

5 洪贏政;陳偉;;微波火災(zāi)探測終端信號處理研究[A];第十屆中國科協(xié)年會論文集（一）[C];2008年

6 柳毅;胡忠日;;視頻火災(zāi)探測在地鐵中的應(yīng)用研究[A];2008鐵路暖通空調(diào)學(xué)術(shù)年會論文集[C];2008年

7 蔣玲;;國外火災(zāi)探測及疏散技術(shù)發(fā)展現(xiàn)狀概述[A];2011中國消防協(xié)會科學(xué)技術(shù)年會論文集[C];2011年

8 張昊;;高大空間場所火災(zāi)探測產(chǎn)品的適用性及設(shè)置應(yīng)用[A];2011中國消防協(xié)會科學(xué)技術(shù)年會論文集[C];2011年

9 劉昕;;火災(zāi)探測報警控制系統(tǒng)及其死機(jī)和復(fù)位[A];第七屆北京青年科技論文評選獲獎?wù)撐募痆C];2003年

10 高俊林;余仲秋;孟偉;;大曠場分布式紅外火災(zāi)探測研究[A];中國儀器儀表學(xué)會第九屆青年學(xué)術(shù)會議論文集[C];2007年

相關(guān)重要報紙文章 前10條

1 記者　李陳續(xù)　通訊員　胡勝友;我火災(zāi)探測與滅火集成技術(shù)實(shí)現(xiàn)智能化[N];光明日報;2005年

2 駐山東記者 黃亦鏹　通訊員 李豹松 紀(jì)永紅;青島推廣普及獨(dú)立式火災(zāi)探測報警器[N];中華建筑報;2011年

3 金曉;天津市取得初步成效[N];人民公安報·消防周刊;2007年

4 朱磊;中國企業(yè)包攬“金牌”[N];人民日報;2008年

5 劉愛國邋特約記者 李書寶;十項(xiàng)硬性措施集中整治“三合一”場所[N];洛陽日報;2007年

6 何鐵軍;貴州省為獨(dú)立式感煙火災(zāi)探測報警裝置立標(biāo)[N];人民公安報·消防周刊;2007年

7 消宣;公安部消防局推廣一批新技術(shù)[N];人民公安報·消防周刊;2006年

8 邵紅旗;我市推進(jìn)消防安全集中整治工作[N];周口日報;2007年

9 記者 查予然 通訊員 林敏;三年內(nèi)徹底清除“三合一”場所[N];安慶日報;2011年

10 記者 張黎明;出租房定消防標(biāo)準(zhǔn)：若被亮“紅牌”不能出租[N];金華日報;2011年

相關(guān)博士學(xué)位論文 前3條

1 賈陽;基于顯著性檢測和煙霧時空特征的視頻火災(zāi)探測方法研究[D];中國科學(xué)技術(shù)大學(xué);2016年

2 高雪清;光纖光柵感溫火災(zāi)探測方法的研究[D];武漢理工大學(xué);2006年

3 厲劍;火災(zāi)探測信號處理算法及其性能評估方法研究[D];大連理工大學(xué);2006年

相關(guān)碩士學(xué)位論文 前10條

1 孫貫華;基于光電感煙的火災(zāi)探測報警器的設(shè)計(jì)與實(shí)現(xiàn)[D];東北大學(xué);2013年

2 雷倩茹;基于信息融合技術(shù)的火災(zāi)探測方法研究[D];華北電力大學(xué)（北京）;2010年

3 張留生;基于多傳感器信息融合的智能建筑火災(zāi)探測研究[D];江西理工大學(xué);2013年

4 張瑋;火災(zāi)探測及聯(lián)動報警系統(tǒng)的設(shè)計(jì)[D];河北科技大學(xué);2010年

5 李小亞;基于人工智能的數(shù)據(jù)融合技術(shù)在火災(zāi)探測中的應(yīng)用研究[D];廣東工業(yè)大學(xué);2005年

6 高強(qiáng);基于模糊神經(jīng)網(wǎng)絡(luò)火災(zāi)智能報警系統(tǒng)的研究[D];沈陽航空工業(yè)學(xué)院;2007年

7 張晶;多傳感器信息融合在火災(zāi)探測中的應(yīng)用研究[D];廣東工業(yè)大學(xué);2003年

8 陳瑩;大空間圖像型火災(zāi)探測和自動滅火技術(shù)的研究[D];天津大學(xué);2006年

9 白巍;FBG感溫火災(zāi)探測中的信號處理研究[D];武漢理工大學(xué);2006年

10 薛節(jié);圖像型火災(zāi)探測及火源定位系統(tǒng)的研究與實(shí)現(xiàn)[D];東華大學(xué);2015年

，

本文編號：2508649