【摘要】：目標(biāo)跟蹤是計(jì)算機(jī)視覺領(lǐng)域的主要研究方向之—,在視頻監(jiān)控、軍事制導(dǎo)、無人駕駛、人機(jī)交互等領(lǐng)域得到了廣泛應(yīng)用,深受研究者們的廣泛關(guān)注。作為目標(biāo)跟蹤技術(shù)的一個(gè)重要分支,多源目標(biāo)跟蹤是通過將來自多個(gè)傳感器的圖像數(shù)據(jù)進(jìn)行聯(lián)合來完成目標(biāo)跟蹤的。由于它利用了各傳感數(shù)據(jù)的冗余互補(bǔ)特性,因此能獲得比單個(gè)傳感器更好的跟蹤性能。紅外與可見光圖像目標(biāo)的融合跟蹤是被研究最多的一種,如何高效準(zhǔn)確的在傳感器中呈現(xiàn)跟蹤目標(biāo)并分析出運(yùn)動(dòng)狀態(tài)的變化,從而獲得對(duì)實(shí)際應(yīng)用有意義的信息是目前多源跟蹤亟待解決的問題。針對(duì)這些問題,本文開展了基于稀疏表示的多源目標(biāo)融合跟蹤方法研究。主要工作如下:1、提出了基于L1-APG紅外與可見光目標(biāo)融合跟蹤的算法。首先,該方法將稀疏表示引入融合跟蹤中,建立了紅外與可見光目標(biāo)的聯(lián)合稀疏表示模型;然后,以它們的聯(lián)合重構(gòu)誤差最小為目標(biāo)來構(gòu)建L1最優(yōu)化問題。并采用APG算法來求解L1問題;最后,利用最小二乘邊界誤差來減少粒子重采樣的次數(shù),達(dá)到降低整個(gè)算法時(shí)間復(fù)雜度的目的,從而實(shí)現(xiàn)了實(shí)時(shí)融合跟蹤。2、提出了基于遮擋檢測(cè)的紅外與可見光目標(biāo)融合跟蹤算法。通過對(duì)目標(biāo)圖像進(jìn)行稀疏表示來描述目標(biāo)的外觀模型,并在稀疏表示的基礎(chǔ)上引入跟蹤和識(shí)別同時(shí)進(jìn)行的方法。為了解決目標(biāo)模板更新過程中所存在的被遮擋的跟蹤結(jié)果被不當(dāng)?shù)靥砑拥絽⒖寄０寮现械膯栴},本文建立了遮擋檢測(cè)模型來計(jì)算被遮擋區(qū)域的大小,并根據(jù)遮擋面積大小使用協(xié)同學(xué)習(xí)的方法來更新參考模型,從而降低遮擋因素對(duì)跟蹤結(jié)果的影響。對(duì)多組紅外與可見光圖像序列對(duì)的測(cè)試結(jié)果表明,本文所提出的兩種跟蹤方法在處理目標(biāo)交匯,目標(biāo)旋轉(zhuǎn),光照變化,以及目標(biāo)遮擋等方面都表現(xiàn)良好。
[Abstract]:Target tracking is one of the main research directions in the field of computer vision. It has been widely used in video surveillance, military guidance, unmanned driving, human-computer interaction and so on. As an important branch of target tracking technology, multi-source target tracking is accomplished by combining image data from multiple sensors. Because it takes advantage of the redundant and complementary characteristics of each sensor data, it can achieve better tracking performance than a single sensor. The fusion tracking of infrared and visible image targets is one of the most studied, how to efficiently and accurately present the tracking target in the sensor and analyze the change of the moving state. Therefore, obtaining meaningful information for practical applications is an urgent problem to be solved in multi-source tracking. In order to solve these problems, a sparse representation based multi-source target fusion and tracking method is proposed in this paper. The main work is as follows: 1. A fusion and tracking algorithm based on L1-APG infrared and visible light target is proposed. Firstly, the sparse representation is introduced into fusion tracking, and the joint sparse representation model of infrared and visible targets is established, and then the L1 optimization problem is constructed with the minimum joint reconstruction error as the target. APG algorithm is used to solve L1 problem. Finally, the least square boundary error is used to reduce the times of particle resampling, and the time complexity of the whole algorithm is reduced, and the real-time fusion tracking is realized. An infrared and visible target fusion and tracking algorithm based on occlusion detection is proposed. The appearance model of the target is described by sparse representation of the target image, and a simultaneous tracking and recognition method is introduced based on the sparse representation. In order to solve the problem that the occluded tracking results are improperly added to the reference template set during the target template updating process, a occlusion detection model is established to calculate the size of the occluded region. According to the size of occlusion area, the reference model is updated by using cooperative learning method, so as to reduce the influence of occlusion factors on the tracking results. The test results of multiple infrared and visible image sequences show that the two tracking methods presented in this paper have a good performance in dealing with the intersection of targets, the rotation of targets, the variation of illumination and the occlusion of targets.
【學(xué)位授予單位】：廣西師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 田浩;巨永鋒;王培;;改進(jìn)的抗遮擋MeanShift目標(biāo)跟蹤算法[J];計(jì)算機(jī)工程與應(yīng)用;2016年06期

2 劉華軍;賴少發(fā);;汽車毫米波雷達(dá)目標(biāo)跟蹤的快速平方根CKF算法[J];南京理工大學(xué)學(xué)報(bào);2016年01期

3 Xiao YUN;Zhongliang JING;Gang XIAO;Bo JIN;Canlong ZHANG;;A compressive tracking based on time-space Kalman fusion model[J];Science China(Information Sciences);2016年01期

4 張燦龍;唐艷平;李志欣;馬海菲;蔡冰;;基于二階空間直方圖的雙核跟蹤[J];電子與信息學(xué)報(bào);2015年07期

5 齊苑辰;吳成東;陳東岳;陸云松;;基于稀疏表達(dá)的超像素跟蹤算法[J];電子與信息學(xué)報(bào);2015年03期

6 陳思;蘇松志;李紹滋;呂艷萍;曹冬林;;基于在線半監(jiān)督boosting的協(xié)同訓(xùn)練目標(biāo)跟蹤算法[J];電子與信息學(xué)報(bào);2014年04期

7 杜凱;巨永鋒;靳引利;李剛;;自適應(yīng)分塊顏色直方圖的MeanShift跟蹤算法[J];武漢理工大學(xué)學(xué)報(bào);2012年06期

8 ;A multi-cue mean-shift target tracking approach based on fuzzified region dynamic image fusion[J];Science China(Information Sciences);2012年03期

9 ;Fusion tracking in color and infrared images using joint sparse representation[J];Science China(Information Sciences);2012年03期

，

本文編號(hào)：2382464