發(fā)布時(shí)間：2019-05-23 11:02

【摘要】：基于視頻監(jiān)控的目標(biāo)跟蹤技術(shù)一直是計(jì)算機(jī)視覺(jué)領(lǐng)域的熱點(diǎn)研究問(wèn)題,在軍事制導(dǎo)、安防建設(shè)和智能交通領(lǐng)域有著廣闊的應(yīng)用前景。智能視頻監(jiān)控系統(tǒng)包括:視頻采集模塊、圖像預(yù)處理模塊、目標(biāo)檢測(cè)模塊、目標(biāo)跟蹤模塊和智能分析模塊,涉及到模式識(shí)別、視覺(jué)分析等多個(gè)領(lǐng)域。在視頻監(jiān)控系統(tǒng)中,由于背景的復(fù)雜多變,目標(biāo)在運(yùn)動(dòng)過(guò)程中經(jīng)常會(huì)出現(xiàn)部分或全部被遮擋的情況。本文針對(duì)目標(biāo)跟蹤過(guò)程中普遍存在的遮擋后目標(biāo)易跟錯(cuò)、跟丟的問(wèn)題展開(kāi)研究,提出了基于“物體恒存性”的方法解決長(zhǎng)時(shí)間遮擋后目標(biāo)容易跟錯(cuò)和丟失的情況,有效的解決了單目標(biāo)和多目標(biāo)跟蹤過(guò)程中長(zhǎng)時(shí)間遮擋問(wèn)題。主要研究?jī)?nèi)容包括:(1)在運(yùn)動(dòng)目標(biāo)檢測(cè)方面,針對(duì)視頻監(jiān)控中的背景不穩(wěn)定的情況,本文采用混合高斯背景建模方法提取前景運(yùn)動(dòng)目標(biāo),利用開(kāi)、閉運(yùn)算等方法對(duì)二值化的前景目標(biāo)進(jìn)行連通性處理,去除噪聲點(diǎn),填補(bǔ)細(xì)小的孔洞,獲得較為完整的目標(biāo)圖像。(2)在運(yùn)動(dòng)目標(biāo)跟蹤方面,提取運(yùn)動(dòng)目標(biāo)的多種類(lèi)型特征,主要包括顏色、邊緣、紋理、直方圖等,并與目標(biāo)運(yùn)動(dòng)軌跡特征相結(jié)合,重點(diǎn)解決目標(biāo)跟蹤過(guò)程中被短時(shí)間遮擋后,單一特征消失,目標(biāo)容易跟錯(cuò)和跟丟的問(wèn)題。針對(duì)長(zhǎng)時(shí)間遮擋情況,本文提出了基于“物體恒存性”算法,分析遮擋關(guān)系,利用目標(biāo)未遮擋時(shí)提取的多種類(lèi)型的特征,在遮擋物的附近快速的查找消失目標(biāo),提高查找的效率。(3)對(duì)本文提出的“物體恒存性”算法,利用“Weizmann”、“KTH”、“CAVIAR”標(biāo)準(zhǔn)視頻庫(kù)以及自錄的視頻序列進(jìn)行實(shí)驗(yàn)驗(yàn)證。針對(duì)跟蹤過(guò)程中可能出現(xiàn)的光照突變、短時(shí)間遮擋、長(zhǎng)時(shí)間遮擋以及循環(huán)遮擋等情況,給出了實(shí)驗(yàn)結(jié)果和分析,表明該算法能夠有效地解決遮擋問(wèn)題,達(dá)到很好的識(shí)別跟蹤效果。
[Abstract]:Target tracking technology based on video surveillance has always been a hot research issue in the field of computer vision, and has a broad application prospect in the fields of military guidance, security construction and intelligent transportation. Intelligent video surveillance system includes: video capture module, image preprocessing module, target detection module, target tracking module and intelligent analysis module, involving pattern recognition, visual analysis and other fields. In video surveillance system, due to the complexity and variability of the background, the target is often partially or completely blocked in the process of motion. In this paper, the problem that the target is easy to follow and lose after occlusion is studied in the process of target tracking, and a method based on "object persistence" is proposed to solve the problem that the target is easy to follow and lose after long time occlusion. It effectively solves the problem of long time occlusion in the process of single target and multi-target tracking. The main research contents are as follows: (1) in the aspect of moving target detection, in view of the unstable background in video surveillance, this paper uses the hybrid Gao Si background modeling method to extract the foreground moving target, using the open, Closed operation and other methods are used to deal with binarization foreground targets, remove noise points, fill small holes, and obtain more complete target images. (2) in moving target tracking, various types of features of moving targets are extracted. It mainly includes color, edge, texture, histogram and so on, and combines with the moving trajectory feature of the target, which focuses on solving the problem that the single feature disappears after a short time occlusion in the process of target tracking, and the target is easy to follow up and lose. In order to solve the problem of long time occlusion, this paper proposes an algorithm based on "object persistence", which analyzes the occlusion relationship and makes use of various types of features extracted by the target when it is not occlusive to quickly find the disappeared target near the occlusive object. (3) the "object persistence" algorithm proposed in this paper is verified by "Weizmann", "KTH", "CAVIAR" standard video libraries and self-recorded video sequences. In view of the possible light mutation, short time occlusion, long time occlusion and cyclic occlusion in the tracking process, the experimental results and analysis show that the algorithm can effectively solve the occlusion problem. Achieve a good recognition and tracking effect.
【學(xué)位授予單位】：河北工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TN948.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 李健勇;徐連宇;;一種融合遮擋分割的多目標(biāo)跟蹤算法[J];電訊技術(shù);2013年02期

2 路紅;李宏勝;費(fèi)樹(shù)岷;郭婧;李文成;;抗遮擋的自適應(yīng)運(yùn)動(dòng)目標(biāo)跟蹤方法[J];計(jì)算機(jī)工程與設(shè)計(jì);2012年06期

3 顏佳;吳敏淵;陳淑珍;張青林;;應(yīng)用Mean Shift和分塊的抗遮擋跟蹤[J];光學(xué)精密工程;2010年06期

4 薛陳;朱明;劉春香;;遮擋情況下目標(biāo)跟蹤算法綜述[J];中國(guó)光學(xué)與應(yīng)用光學(xué);2009年05期

5 陳磊;鄒北驥;;基于動(dòng)態(tài)閾值對(duì)稱(chēng)差分和背景差法的運(yùn)動(dòng)對(duì)象檢測(cè)算法[J];計(jì)算機(jī)應(yīng)用研究;2008年02期

6 齊麗娜;張博;王戰(zhàn)凱;;最大類(lèi)間方差法在圖像處理中的應(yīng)用[J];無(wú)線(xiàn)電工程;2006年07期

7 常發(fā)亮;馬麗;喬誼正;;遮擋情況下基于特征相關(guān)匹配的目標(biāo)跟蹤算法[J];中國(guó)圖象圖形學(xué)報(bào);2006年06期

8 馮俊萍,趙轉(zhuǎn)萍,徐濤;基于數(shù)學(xué)形態(tài)學(xué)的圖像邊緣檢測(cè)技術(shù)[J];航空計(jì)算技術(shù);2004年03期

9 韓思奇,王蕾;圖像分割的閾值法綜述[J];系統(tǒng)工程與電子技術(shù);2002年06期

相關(guān)博士學(xué)位論文 前1條

1 李崢;智能視頻監(jiān)控中的遮擋目標(biāo)跟蹤技術(shù)研究[D];華中科技大學(xué);2008年

，

本文編號(hào)：2483846