本文選題：前景檢測(cè) + 人群運(yùn)動(dòng)特征��； 參考：《西安理工大學(xué)》2017年碩士論文

【摘要】：人們的公共安全意識(shí)在不斷增強(qiáng),眾多公共場(chǎng)所的人群管理具有重要的現(xiàn)實(shí)意義。目前人群密度估計(jì)與人群異常行為檢測(cè)技術(shù)是人群監(jiān)控管理的兩個(gè)重要方面,具有極大的實(shí)用價(jià)值。針對(duì)人群突然向四處逃跑、群毆等人群異常事件,本文結(jié)合人群運(yùn)動(dòng)特征和人群密度特征來(lái)檢測(cè)人群異常行為,研究?jī)?nèi)容涉及前景提取算法、特征點(diǎn)提取與跟蹤算法、人群密度特征提取方法、人群運(yùn)動(dòng)特征提取方法以及人群異常檢測(cè)算法。本文主要研究工作如下:(1)研究分析常用運(yùn)動(dòng)目標(biāo)檢測(cè)算法,在此基礎(chǔ)上本文設(shè)計(jì)實(shí)現(xiàn)了一種Vibe改進(jìn)算法,改進(jìn)算法能改善Vibe算法中產(chǎn)生的鬼影及陰影問(wèn)題,并且在光照突變下也能進(jìn)行有效檢測(cè),測(cè)試結(jié)果表明了本文改進(jìn)算法可以較準(zhǔn)確地檢測(cè)出場(chǎng)景中的運(yùn)動(dòng)目標(biāo)。(2)在提取到前景運(yùn)動(dòng)目標(biāo)之后,本文提出使用運(yùn)動(dòng)特征變化率表征人群的運(yùn)動(dòng)信息,首先通過(guò)金字塔LK光流法跟蹤前景圖像的特征點(diǎn)計(jì)算出運(yùn)動(dòng)目標(biāo)的運(yùn)動(dòng)向量,并統(tǒng)計(jì)視頻幀塊區(qū)間內(nèi)的特征點(diǎn)來(lái)表征人群的分布狀態(tài),結(jié)合運(yùn)動(dòng)向量和分布狀態(tài)形成人群運(yùn)動(dòng)特征變化率描述人群運(yùn)動(dòng)信息。隨后通過(guò)前景圖像像素?cái)?shù)對(duì)人群密度視頻圖像分類(lèi),若為稀疏人群圖像則提取前景特征點(diǎn)數(shù)、前景像素總面積、邊緣特征和周長(zhǎng)面積比特征描述人群密度信息,若為密集人群圖像則提取前景圖的局部二值模式灰度共生矩陣特征和灰度圖的局部二值模式灰度共生矩陣特征描述人群密度特征。(3)研究分析現(xiàn)有人群異常檢測(cè)方法,在此基礎(chǔ)上本文將人群運(yùn)動(dòng)特征和人群密度特征結(jié)合檢測(cè)人群異常行為。通過(guò)采用標(biāo)準(zhǔn)視頻數(shù)據(jù)集UMN數(shù)據(jù)集對(duì)采取人群運(yùn)動(dòng)特征、人群運(yùn)動(dòng)和方向特征、人群運(yùn)動(dòng)特征變化率的方法進(jìn)行實(shí)驗(yàn)對(duì)比,實(shí)驗(yàn)驗(yàn)證了本文方法在準(zhǔn)確率和實(shí)時(shí)性上較好的表現(xiàn)。
[Abstract]:People's public safety consciousness is increasing constantly, the crowd management of numerous public places has important practical significance. At present, crowd density estimation and abnormal behavior detection are two important aspects of crowd monitoring and management, and have great practical value. In view of the abnormal events of the crowd, such as the sudden flight of the crowd and the fight, this paper combines the characteristics of the crowd movement and the density of the crowd to detect the abnormal behavior of the crowd. The research involves the foreground extraction algorithm, the feature point extraction and tracking algorithm. Population density feature extraction method, crowd motion feature extraction method and crowd anomaly detection algorithm. The main work of this paper is as follows: (1) Research and analysis of commonly used moving target detection algorithms. On this basis, an improved Vibe algorithm is designed and implemented. The improved algorithm can improve the ghost and shadow problems in the Vibe algorithm. The test results show that the improved algorithm can accurately detect the moving target in the scene. In this paper, the motion information of the population is represented by the change rate of the motion feature. Firstly, the motion vector of the moving object is calculated by tracking the feature points of the foreground image by the pyramid LK optical flow method. The feature points in the video frame block interval are counted to represent the distribution state of the population, and the population motion information is described by combining the motion vector and the distribution state to form the change rate of the crowd motion characteristics. Then the population density video image is classified by the pixel number of foreground image, the foreground feature points are extracted if the image is sparse, the total area of foreground pixel, edge feature and circumference area ratio feature to describe the population density information. If it is a dense crowd image, it extracts the local binary pattern gray level co-occurrence matrix feature of foreground map and the local binary pattern gray level co-occurrence matrix feature of gray scale map to describe the population density characteristic. On this basis, the characteristics of population movement and population density are combined to detect the abnormal behavior of the population. By using the standard video data set UMN data set, the methods of adopting crowd motion feature, crowd movement and direction feature, and the change rate of crowd motion feature are compared experimentally. Experimental results show that the proposed method performs well in accuracy and real-time performance.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：D63;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 史瑞環(huán);吳斌;李務(wù)軍;范風(fēng)兵;;一種改進(jìn)的融合幀差法的ViBe算法[J];微型機(jī)與應(yīng)用;2016年04期

2 蔡瑞初;謝偉浩;郝志峰;王麗娟;溫雯;;基于多尺度時(shí)間遞歸神經(jīng)網(wǎng)絡(luò)的人群異常檢測(cè)[J];軟件學(xué)報(bào);2015年11期

3 王強(qiáng);孫紅;;基于像素統(tǒng)計(jì)和紋理特征的人群密度估計(jì)[J];電子科技;2015年07期

4 周潔;郭立君;張榮;;基于粒子熵值的異常行為檢測(cè)[J];無(wú)線電通信技術(shù);2015年03期

5 汪雙承;管業(yè)鵬;;基于粒子流和能量模型的異常行為檢測(cè)[J];電子器件;2014年06期

6 劉賞;梁茜;董林芳;;“幀平均加速度”人群異常運(yùn)動(dòng)檢測(cè)算法[J];計(jì)算機(jī)工程與應(yīng)用;2015年21期

7 薛陳;;復(fù)雜場(chǎng)景下的人數(shù)統(tǒng)計(jì)[J];電子測(cè)量技術(shù);2012年12期

8 李媛;張艷珠;渠彪;李小娟;;HSV空間特征和紋理特征的陰影檢測(cè)算法研究[J];沈陽(yáng)理工大學(xué)學(xué)報(bào);2012年04期

9 楊琳;苗振江;;一種人群異常行為檢測(cè)系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];鐵路計(jì)算機(jī)應(yīng)用;2010年07期

10 胡芝蘭;江帆;王貴錦;林行剛;嚴(yán)洪;;基于運(yùn)動(dòng)方向的異常行為檢測(cè)[J];自動(dòng)化學(xué)報(bào);2008年11期

相關(guān)博士學(xué)位論文 前1條

1 梁華;多攝像機(jī)視頻監(jiān)控中運(yùn)動(dòng)目標(biāo)檢測(cè)與跟蹤[D];國(guó)防科學(xué)技術(shù)大學(xué);2009年

相關(guān)碩士學(xué)位論文 前4條

1 劉倩男;基于視頻的人群異常檢測(cè)方法研究[D];重慶大學(xué);2016年

2 張鴿;人群異常狀態(tài)檢測(cè)算法研究[D];電子科技大學(xué);2015年

3 林沁;視頻中的大規(guī)模人群密度與異常行為分析[D];廈門(mén)大學(xué);2014年

4 張q，

本文編號(hào)：1823787