【摘要】：在過(guò)去的幾十年中,行人目標(biāo)跟蹤技術(shù)已經(jīng)成為了計(jì)算機(jī)視覺(jué)領(lǐng)域最熱門(mén)的課題之一。許多學(xué)者對(duì)行人目標(biāo)跟蹤技術(shù)進(jìn)行了大量的研究,促進(jìn)了其的快速發(fā)展。但是當(dāng)把視頻序列應(yīng)用到現(xiàn)實(shí)生活中時(shí),跟蹤器需要處理很多難題,例如遮擋、相似物干擾、光照變化、尺度變化以及背景雜亂等。在這些難題中,遮擋是最棘手的問(wèn)題之一�；诖�,為解決復(fù)雜遮擋情況下的行人目標(biāo)跟蹤問(wèn)題,本文對(duì)行人目標(biāo)跟蹤中的外觀模型建模、狀態(tài)估計(jì)和遮擋檢測(cè)等幾個(gè)關(guān)鍵技術(shù)問(wèn)題進(jìn)行了深入研究。具體研究?jī)?nèi)容如下:針對(duì)行人目標(biāo)在遮擋狀態(tài)下容易產(chǎn)生跟蹤漂移的問(wèn)題,提出一種基于重構(gòu)誤差方差的粒子濾波行人目標(biāo)跟蹤算法(VREPT)。該算法在粒子濾波跟蹤框架下,采用主成分分析方法建立目標(biāo)外觀模型;然后,為了處理遮擋干擾問(wèn)題,在跟蹤系統(tǒng)中引入遮擋檢測(cè)器,對(duì)視頻序列中每一幀的跟蹤結(jié)果,根據(jù)重構(gòu)誤差的方差檢測(cè)目標(biāo)是否處于遮擋狀態(tài),并依據(jù)檢測(cè)結(jié)果進(jìn)行相應(yīng)的遮擋處理;當(dāng)檢測(cè)到目標(biāo)處于被遮擋狀態(tài)時(shí),目標(biāo)模板將停止更新,當(dāng)目標(biāo)未被遮擋時(shí),采用一種增量方式有效學(xué)習(xí)和更新目標(biāo)外觀模型。實(shí)驗(yàn)結(jié)果表明,提出的算法能夠有效地處理遮擋,并且能夠?qū)δ繕?biāo)進(jìn)行準(zhǔn)確穩(wěn)定地跟蹤。針對(duì)行人目標(biāo)跟蹤中目標(biāo)遮擋的快速檢測(cè)問(wèn)題,提出一種基于高階累積量的行人目標(biāo)跟蹤算法(HOCPT)。在提出的算法中,利用高階累積量能夠有效抑制高斯噪聲的特性,構(gòu)造重構(gòu)誤差的三階累積量,并以此構(gòu)建目標(biāo)遮擋檢測(cè)器對(duì)行人目標(biāo)進(jìn)行遮擋檢測(cè),實(shí)現(xiàn)對(duì)遮擋目標(biāo)的快速實(shí)時(shí)檢測(cè)和處理。實(shí)驗(yàn)結(jié)果表明,提出算法能夠準(zhǔn)確而快速地檢測(cè)到目標(biāo)進(jìn)入和離開(kāi)遮擋的時(shí)刻,并對(duì)遮擋問(wèn)題進(jìn)行有效的處理,具有穩(wěn)健的跟蹤效果。
[Abstract]:In the past few decades, pedestrian target tracking technology has become one of the hottest topics in the field of computer vision. Many scholars have done a lot of research on pedestrian target tracking technology to promote its rapid development. However, when video sequences are applied to real life, the tracker needs to deal with many problems, such as occlusion, similarity interference, illumination change, scale change and background clutter. Of these problems, occlusion is one of the thorniest. Based on this, in order to solve the problem of pedestrian target tracking in the case of complex occlusion, several key technical problems such as appearance model modeling, state estimation and occlusion detection in pedestrian target tracking are studied in this paper. The specific research contents are as follows: aiming at the problem that pedestrian target is easy to track drift in occlusion state, a particle filter pedestrian target tracking algorithm (VREPT). Based on reconstruction error variance is proposed. In the framework of particle filter tracking, the method of principal component analysis (PCA) is used to establish the object appearance model. Then, in order to deal with the occlusion interference problem, the occlusion detector is introduced into the tracking system. The tracking results of each frame in the video sequence are detected according to the variance of the reconstruction error. According to the test results, the corresponding occlusion treatment is carried out. When the target is detected to be occluded, the target template will stop updating, and when the target is not occluded, an incremental approach will be used to effectively learn and update the target appearance model. Experimental results show that the proposed algorithm can deal with occlusion effectively and can track the target accurately and stably. Aiming at the problem of fast detection of target occlusion in pedestrian target tracking, a pedestrian target tracking algorithm (HOCPT). Based on high order cumulants is proposed. In the proposed algorithm, the feature of Gao Si noise can be effectively suppressed by using high-order cumulants, and the third-order cumulant of reconstruction error can be constructed, and the target occlusion detector is constructed to detect pedestrian targets. The fast real-time detection and processing of occlusion targets are realized. Experimental results show that the proposed algorithm can accurately and quickly detect the entry and departure of the target occlusion, and effectively deal with the occlusion problem, and has a robust tracking effect.
【學(xué)位授予單位】：深圳大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 李俊;謝維信;李良群;;基于空時(shí)線索的TLD視頻跟蹤算法[J];信號(hào)處理;2015年10期

2 孫銳;黃靜茹;丁文秀;;一種基于子空間學(xué)習(xí)的實(shí)時(shí)目標(biāo)跟蹤算法[J];光電工程;2015年02期

3 武斌;姬紅兵;李鵬;;基于三階累積量的紅外弱小運(yùn)動(dòng)目標(biāo)檢測(cè)新方法[J];紅外與毫米波學(xué)報(bào);2006年05期

4 宋驪平,姬紅兵,高新波;基于高階累積量的目標(biāo)機(jī)動(dòng)檢測(cè)新方法[J];電子學(xué)報(bào);2004年01期

，

本文編號(hào)：2314521