【摘要】：隨著國(guó)家經(jīng)濟(jì)的快速發(fā)展,時(shí)常發(fā)生的火災(zāi)給工業(yè)生產(chǎn)帶來(lái)了巨大的損失。傳統(tǒng)的火災(zāi)探測(cè)傳感器雖然對(duì)火災(zāi)的預(yù)防具有重要的意義,但它們有很多的局限性,尤其在復(fù)雜的工廠生產(chǎn)環(huán)境中。為了解決傳統(tǒng)的檢測(cè)傳感器在一些環(huán)境的使用缺陷,國(guó)內(nèi)外很多學(xué)者對(duì)視頻火災(zāi)檢測(cè)算法進(jìn)行了研究。本文針對(duì)火災(zāi)檢測(cè)技術(shù)的研究進(jìn)行了如下工作:(1)首先對(duì)火災(zāi)檢測(cè)技術(shù)的發(fā)展現(xiàn)狀進(jìn)行綜述,分析了傳統(tǒng)的火災(zāi)探測(cè)技術(shù)的缺陷,然后分析了國(guó)內(nèi)外機(jī)器視覺(jué)火災(zāi)探測(cè)發(fā)展現(xiàn)狀,介紹了各個(gè)學(xué)者提出的視頻圖像檢測(cè)算法,最后得出這些技術(shù)只能在某些特殊的場(chǎng)合應(yīng)用。(2)針對(duì)顏色檢測(cè)算法、移動(dòng)物體檢測(cè)算法和紅外光譜火焰檢測(cè)算法進(jìn)行研究。其中顏色檢測(cè)算法是基于統(tǒng)計(jì)學(xué)原理的方法;移動(dòng)物體檢測(cè)主要包括差分法、光流法、高斯背景減除算法;本文對(duì)其進(jìn)行了深入的推導(dǎo)。(3)針對(duì)火焰的特征分類(lèi)算法進(jìn)行研究,在總結(jié)這些算法的基礎(chǔ)上,我們提出了一種火災(zāi)檢測(cè)方法,該方法結(jié)合背景減除算法和區(qū)域協(xié)方差算子,首先用顏色分布模型和自適應(yīng)的背景減除算法對(duì)視頻圖像進(jìn)行預(yù)處理,然后提取時(shí)空協(xié)方差矩陣。最后用支持向量機(jī)對(duì)視頻數(shù)據(jù)進(jìn)行分類(lèi),得出火焰區(qū)域。并和已有文獻(xiàn)中的算法效果進(jìn)行了對(duì)比分析。(4)針對(duì)機(jī)床現(xiàn)在應(yīng)用要求,開(kāi)發(fā)了一套機(jī)器視覺(jué)檢測(cè)系統(tǒng),詳細(xì)介紹了機(jī)器視覺(jué)的機(jī)床火災(zāi)控制報(bào)警系統(tǒng)的系統(tǒng)結(jié)構(gòu)、軟件系統(tǒng)、硬件系統(tǒng)。該軟件系統(tǒng)已經(jīng)在北京電加工研究所現(xiàn)場(chǎng)實(shí)際運(yùn)行。經(jīng)測(cè)試,該軟件系統(tǒng)算法可靠性強(qiáng)、探測(cè)率高。能夠滿足電加工機(jī)床現(xiàn)場(chǎng)需要。本文提出了一種火災(zāi)檢測(cè)方法,該方法結(jié)合背景減除算法和區(qū)域協(xié)方差算子。最后用支持向量機(jī)對(duì)視頻數(shù)據(jù)進(jìn)行分類(lèi),得出火焰區(qū)域。針對(duì)北京電加工研究所的特殊應(yīng)用,開(kāi)發(fā)了一套針對(duì)機(jī)床火災(zāi)的機(jī)器視覺(jué)系統(tǒng)。
[Abstract]:With the rapid development of national economy, frequent fires have brought huge losses to industrial production. Although the traditional fire detection sensors are of great significance to fire prevention, they have many limitations, especially in the complex production environment of factories. In order to solve the defects of traditional detection sensors in some environments, many scholars at home and abroad have studied the video fire detection algorithm. In this paper, the research work of fire detection technology is as follows: (1) the development of fire detection technology is summarized, the defects of traditional fire detection technology are analyzed, and the present situation of fire detection by machine vision at home and abroad is analyzed. This paper introduces the video image detection algorithms proposed by various scholars, and concludes that these techniques can only be applied in some special situations. (2) the color detection algorithm, moving object detection algorithm and infrared spectrum flame detection algorithm are studied. Color detection algorithm is based on the principle of statistics; moving object detection mainly includes difference method, optical flow method, Gao Si background subtraction algorithm. On the basis of summarizing these algorithms, we propose a fire detection method, which combines background subtraction algorithm and regional covariance operator. Firstly, the color distribution model and adaptive background subtraction algorithm are used to preprocess the video image. Then the space-time covariance matrix is extracted. Finally, the support vector machine is used to classify the video data and the flame region is obtained. And compared with the existing literature algorithm results. (4) according to the current application requirements of machine tools, a set of machine vision detection system is developed. The system structure and software system of machine tool fire control and alarm system based on machine vision are introduced in detail. Hardware system. The software system has been in practical operation in Beijing Institute of Electrical processing. After testing, the software system has strong reliability and high detectability. Able to meet the field needs of electrical machining machine tools. In this paper, a fire detection method is proposed, which combines background subtraction algorithm and regional covariance operator. Finally, the support vector machine is used to classify the video data and the flame region is obtained. Aiming at the special application of Beijing Institute of Electrical processing, a machine vision system for machine tool fire is developed.
【學(xué)位授予單位】：沈陽(yáng)理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TG502.39;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 楊俊;王潤(rùn)生;;基于計(jì)算機(jī)視覺(jué)的視頻火焰檢測(cè)技術(shù)[J];中國(guó)圖象圖形學(xué)報(bào);2008年07期

2 吳愛(ài)國(guó);李明;陳瑩;;大空間圖像型火災(zāi)探測(cè)算法的研究[J];計(jì)算機(jī)測(cè)量與控制;2006年07期

3 陳瑩;吳愛(ài)國(guó);;基于圖像處理的火災(zāi)監(jiān)測(cè)系統(tǒng)軟件設(shè)計(jì)[J];低壓電器;2006年01期

4 程曉舫,吳建華,徐新宇;CCD影像中高溫目標(biāo)的甄別[J];自然科學(xué)進(jìn)展;2001年03期

5 程曉舫,鄧志華,沙川,王瑞芳;自由火焰影像發(fā)展的測(cè)量和分析[J];應(yīng)用基礎(chǔ)與工程科學(xué)學(xué)報(bào);1998年04期

6 袁宏永,劉炳海,陳曉軍,宗封儀;圖像型火災(zāi)智能自動(dòng)探測(cè)與空間定位技術(shù)[J];消防科技;1998年02期

7 吳龍標(biāo),宋衛(wèi)國(guó),盧結(jié)成;圖象火災(zāi)監(jiān)控中一個(gè)新穎的火災(zāi)判據(jù)[J];火災(zāi)科學(xué);1997年02期

相關(guān)博士學(xué)位論文 前1條

1 榮建忠;基于多特征的火焰圖像探測(cè)研究及實(shí)現(xiàn)[D];中國(guó)科學(xué)技術(shù)大學(xué);2012年

，

本文編號(hào)：2200980