【摘要】：隨著計(jì)算機(jī)技術(shù)、視頻技術(shù)和圖像處理技術(shù)的不斷發(fā)展,基于圖像處理方法的運(yùn)動(dòng)物體識(shí)別技術(shù)被越來越多地運(yùn)用于智能視頻監(jiān)控系統(tǒng)之中。相對(duì)于傳統(tǒng)的識(shí)別方法,圖像處理方法因?yàn)槠洳恍枰鲈O(shè)外部設(shè)備,系統(tǒng)整體成本較低,可擴(kuò)展性強(qiáng)等諸多優(yōu)點(diǎn),正越來越多的受到研究人員和實(shí)際工程人員的關(guān)注。交通視頻監(jiān)控是智能視頻監(jiān)控的一個(gè)重要應(yīng)用領(lǐng)域。 交通視頻自身具有很多特點(diǎn),如視頻分辨率較低、運(yùn)動(dòng)物體背景復(fù)雜、氣象條件多變、存在大范圍光線變化等。本文對(duì)當(dāng)前存在的運(yùn)動(dòng)物體檢測、跟蹤和分類方法,特別是基于視頻圖像處理的方法進(jìn)行了調(diào)研,分析了各種方法的適用場景和優(yōu)缺點(diǎn),并針對(duì)本文實(shí)際的應(yīng)用場景——低分辨率交通視頻圖像——提出了一種基于多特征融合和多幀融合的運(yùn)動(dòng)物體識(shí)別算法。 本文首先對(duì)運(yùn)動(dòng)物體的分割方法進(jìn)行研究,通過對(duì)交通視頻建立合適的背景模型,采用背景差分的方法提取出運(yùn)動(dòng)物體。利用形態(tài)學(xué)處理等方法去除背景噪聲的干擾,并提出了一種基于區(qū)域生長的陰影去除方法,以獲得較為準(zhǔn)確的運(yùn)動(dòng)物體。接著,提取出運(yùn)動(dòng)物體的幾何特征和運(yùn)動(dòng)特征,再分別基于支持向量機(jī)和級(jí)聯(lián)分類器兩種策略對(duì)運(yùn)動(dòng)物體的特征進(jìn)行融合,獲取運(yùn)動(dòng)物體的單幀判決信息。最后融合視頻序列中多幀的判決信息,完成對(duì)運(yùn)動(dòng)物體的識(shí)別,得到最終分類信息。本文給出的這種基于多特征融合和多幀融合的運(yùn)動(dòng)物體識(shí)別算法,經(jīng)實(shí)驗(yàn)證明,在實(shí)際低分辨率交通視頻的應(yīng)用場景中,可以較好地識(shí)別出運(yùn)動(dòng)物體,且計(jì)算復(fù)雜度低,能夠滿足交通視頻的實(shí)時(shí)處理需求。 在完成算法設(shè)計(jì)后,本文對(duì)智能交通視頻監(jiān)控系統(tǒng)的構(gòu)建進(jìn)行了描述,簡要論述了該系統(tǒng)的組成原理、處理流程和實(shí)現(xiàn)方案。
[Abstract]:With the development of computer technology, video technology and image processing technology, moving object recognition technology based on image processing method is more and more used in intelligent video surveillance system. Compared with the traditional recognition methods, the image processing method is paid more and more attention by researchers and practical engineers because it does not need to add external equipment, the overall cost of the system is relatively low, the expansibility is strong and so on. Traffic video surveillance is an important application field of intelligent video surveillance. Traffic video has many characteristics, such as low video resolution, complex background of moving objects, changeable meteorological conditions, large range of light changes and so on. In this paper, the existing methods of moving object detection, tracking and classification, especially based on video image processing, are investigated, and the applicable scenes, advantages and disadvantages of these methods are analyzed. And a moving object recognition algorithm based on multi-feature fusion and multi-frame fusion is proposed for the actual application scene of this paper, which is low resolution traffic video image. In this paper, the segmentation method of moving object is studied firstly, and the moving object is extracted by using background difference method by establishing a suitable background model for traffic video. Morphological processing is used to remove background noise, and a shadow removal method based on region growth is proposed to obtain more accurate moving objects. Then, the geometric features and motion features of moving objects are extracted, and then the features of moving objects are fused based on support vector machine and cascade classifier, respectively, and the single frame decision information of moving objects is obtained. Finally, the decision information of multiple frames in the video sequence is fused to complete the recognition of moving objects and the final classification information is obtained. The motion object recognition algorithm based on multi-feature fusion and multi-frame fusion presented in this paper has been proved by experiments that it can recognize moving objects well in the application scene of actual low-resolution traffic video, and the computational complexity is low. It can meet the need of real-time traffic video processing. After completing the algorithm design, this paper describes the construction of intelligent transportation video surveillance system, and briefly discusses the principle of the system, processing process and implementation scheme.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN948.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 聞帆;屈楨深;閆紀(jì)紅;;集成多特征信息的運(yùn)動(dòng)陰影檢測[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2011年05期

2 魏偉波;芮筱亭;;圖像邊緣檢測方法研究[J];計(jì)算機(jī)工程與應(yīng)用;2006年30期

3 陳柏生;陳鍛生;;基于歸一化rgb彩色模型的運(yùn)動(dòng)陰影檢測[J];計(jì)算機(jī)應(yīng)用;2006年08期

4 盛能;王慧;劉泓;;混合交通流中的自行車識(shí)別及參數(shù)提取[J];計(jì)算機(jī)應(yīng)用研究;2010年05期

5 趙來剛;陳道炯;;一種基于Sobel算子的新型邊緣提取技術(shù)[J];機(jī)械與電子;2011年02期

6 張嘉;梁茵;;論我國城市道路建設(shè)與規(guī)劃管理問題[J];四川建筑;2006年04期

7 余孟澤;劉正熙;駱鍵;楊丹;;融合紋理特征和陰影屬性的陰影檢測方法[J];計(jì)算機(jī)工程與設(shè)計(jì);2011年10期

8 李子龍;劉偉銘;;基于組合特征和HSI顏色空間的陰影檢測[J];微電子學(xué)與計(jì)算機(jī);2011年03期

9 高嵐;董慧穎;蘭利寶;;自適應(yīng)背景下運(yùn)動(dòng)目標(biāo)陰影檢測算法研究[J];現(xiàn)代電子技術(shù);2008年06期

10 ;中國安防行業(yè)“十二五”(2011～2015年)發(fā)展規(guī)劃[J];中國安防;2011年03期

相關(guān)博士學(xué)位論文 前2條

1 李峰;智能視頻監(jiān)控系統(tǒng)中的行人運(yùn)動(dòng)分析研究[D];中國科學(xué)技術(shù)大學(xué);2011年

2 陳功;魯棒的智能視頻監(jiān)控方法研究[D];中國科學(xué)技術(shù)大學(xué);2008年

，

本文編號(hào)：2397015