本文選題：目標(biāo)跟蹤 + 粒子濾波��； 參考：《吉林大學(xué)》2017年碩士論文

【摘要】：計(jì)算機(jī)視覺(jué)包含眾多領(lǐng)域,運(yùn)動(dòng)目標(biāo)跟蹤已經(jīng)成為該領(lǐng)域備受歡迎的研究方向和研究熱點(diǎn)。應(yīng)用范圍和應(yīng)用領(lǐng)域非常之多,例如,智能監(jiān)控,人機(jī)交互,機(jī)器人導(dǎo)航,流量控制,生物醫(yī)療診斷等。到目前為止,雖然國(guó)內(nèi)外專(zhuān)家學(xué)者已經(jīng)提出很多經(jīng)典的算法并且在此基礎(chǔ)上的改進(jìn)算法,但是這些目標(biāo)跟蹤算法在實(shí)際的應(yīng)用中仍然面臨著巨大的挑戰(zhàn),比較常見(jiàn)的有光照變化,遮擋,目標(biāo)突然移動(dòng)所導(dǎo)致的非線性形變,背景與跟蹤目標(biāo)相似度很高以及復(fù)雜背景下的噪聲干擾等因素對(duì)目標(biāo)跟蹤算法速度和準(zhǔn)確性的影響�？赡茉斐呻y以估計(jì)的后果�？紤]遇到的這些問(wèn)題,實(shí)現(xiàn)一種能夠綜合適應(yīng)復(fù)雜場(chǎng)景的目標(biāo)跟蹤算法還是比較艱巨和困難的。目前,粒子濾波是解決非高斯非線性跟蹤問(wèn)題的最佳方法。該算法能夠很好地適應(yīng)多種外界干擾因素的影響,能夠最大程度上保證目標(biāo)跟蹤的準(zhǔn)確性和魯棒性。(1)然而經(jīng)典的粒子濾波算法采用單一特征來(lái)描述待跟蹤的目標(biāo),在跟蹤過(guò)程中容易受到光照,遮擋,目標(biāo)與背景相似等因素的干擾。針對(duì)這個(gè)問(wèn)題,本文將多種目標(biāo)特征融合到粒子濾波中用于目標(biāo)跟蹤。在粒子濾波框架下,綜合考慮各種特征對(duì)不同干擾因素的魯棒性和準(zhǔn)確性,選擇合適的特征提取算法融合其中。運(yùn)用動(dòng)態(tài)計(jì)算的方法計(jì)算不同特征對(duì)目標(biāo)和背景的區(qū)分度和穩(wěn)定性,自動(dòng)選擇區(qū)分度高,穩(wěn)定性好的特征來(lái)表征目標(biāo),形成多特征融合目標(biāo)模型。使用度量特征的不確定性方法來(lái)動(dòng)態(tài)調(diào)整所提取的目標(biāo)特征所占的比重。利用粒子濾波算法本身的顏色特征適應(yīng)目標(biāo)的形變和尺度的變化,利用邊緣特征信息來(lái)適應(yīng)背景的變化以及利用局部二值模式(LBP)特征與圖像幀的灰度信息相結(jié)合來(lái)適應(yīng)光照的變化,使得改進(jìn)后的算法穩(wěn)定性和準(zhǔn)確性更好。(2)盡管上面所提出的算法能夠很好地適應(yīng)大多數(shù)外界環(huán)境因素的變化。但是跟蹤視頻中出現(xiàn)目標(biāo)遮擋時(shí),容易出現(xiàn)目標(biāo)跟蹤偏移或者目標(biāo)跟蹤丟失問(wèn)題。因此本文將目標(biāo)的上下文信息融入粒子濾波框架中來(lái)解決目標(biāo)遮擋的問(wèn)題。由于連續(xù)幀圖像中待跟蹤目標(biāo)與其周?chē)植繄?chǎng)景的上下文關(guān)系是保持相似的。因此可以通過(guò)分析上一幀中目標(biāo)的上下文信息來(lái)估計(jì)下一幀中目標(biāo)的位置。在目標(biāo)存在遮擋時(shí)實(shí)現(xiàn)快速、魯棒性跟蹤。最后,在公共圖像數(shù)據(jù)集上對(duì)本文提出的兩種目標(biāo)跟蹤算法與其他相關(guān)目標(biāo)跟蹤算法的跟蹤性能進(jìn)行對(duì)比。通過(guò)對(duì)實(shí)驗(yàn)結(jié)果進(jìn)行分析,得出結(jié)論:在應(yīng)對(duì)光照變化,遮擋,形變,目標(biāo)與背景相似以及噪聲干擾方面,提出的改進(jìn)算法很大程度上提升了跟蹤準(zhǔn)確性和魯棒性。綜上所述,本文的算法研究可以極大地豐富目標(biāo)跟蹤領(lǐng)域的理論研究并且能夠滿足部分計(jì)算機(jī)視覺(jué)領(lǐng)域的現(xiàn)實(shí)應(yīng)用需求。
[Abstract]:Computer vision includes many fields, and moving target tracking has become a popular research direction and research hotspot in this field. There are many applications, such as intelligent monitoring, human-computer interaction, robot navigation, flow control, biomedical diagnosis and so on. Up to now, although experts and scholars at home and abroad have proposed a lot of classical algorithms and improved algorithms on this basis, these target tracking algorithms are still facing enormous challenges in practical applications. Some common factors, such as illumination variation, occlusion, nonlinear deformation caused by sudden moving of target, high similarity between background and tracking object and noise interference in complex background, affect the speed and accuracy of target tracking algorithm. It can have incalculable consequences. Considering these problems, it is difficult and difficult to implement a target tracking algorithm which can adapt to complex scenes. At present, particle filter is the best method to solve non-Gao Si nonlinear tracking problem. The algorithm can adapt to the influence of many kinds of external interference factors and ensure the accuracy and robustness of target tracking to the greatest extent. However, the classical particle filter algorithm uses a single feature to describe the target to be tracked. In the process of tracking, it is easy to be interfered by illumination, occlusion, similarity between target and background, and so on. In order to solve this problem, a variety of target features are fused to particle filter for target tracking. In the framework of particle filter, considering the robustness and accuracy of various features to different interference factors, the appropriate feature extraction algorithm is selected. The method of dynamic calculation is used to calculate the discrimination and stability of different features to target and background. The features with high degree of discrimination and good stability are automatically selected to represent the target and form a multi-feature fusion target model. The uncertainty method of measuring features is used to dynamically adjust the proportion of extracted target features. The color feature of particle filter algorithm is used to adapt to the deformation and scale change of the target. The edge feature information is used to adapt to the background change, and the local binary mode LBP) feature is combined with the gray level information of the image frame to adapt to the illumination change. It makes the improved algorithm more stable and accurate.) although the proposed algorithm can well adapt to the changes of most external environmental factors. However, when the target occlusion occurs in the tracking video, the target tracking offset or the target tracking loss is easy to occur. Therefore, the contextual information of the target is incorporated into the particle filter framework to solve the occlusion problem. Because the contextual relationship between the target to be tracked and the local scene around it is similar in successive frame images. Therefore, the location of the target in the previous frame can be estimated by analyzing the context information of the target in the previous frame. Fast and robust tracking is achieved when there is occlusion. Finally, the performance of the two target tracking algorithms proposed in this paper is compared with that of other related target tracking algorithms on the common image data set. Through the analysis of the experimental results, it is concluded that the proposed improved algorithm improves the tracking accuracy and robustness to a great extent in dealing with changes of illumination, occlusion, deformation, similarity between target and background, and noise interference. To sum up, the algorithm research in this paper can greatly enrich the theoretical research in the field of target tracking and can meet the practical application requirements of some computer vision fields.
【學(xué)位授予單位】：吉林大學(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8條

1 瞿俊峰;沈星辰;倪進(jìn)園;;多視角目標(biāo)檢測(cè)與跟蹤技術(shù)的研究與實(shí)現(xiàn)[J];科技創(chuàng)新與應(yīng)用;2016年36期

2 黃馨譽(yù);胡士強(qiáng);鄭世友;;基于PN學(xué)習(xí)的雷達(dá)目標(biāo)魯棒跟蹤算法[J];傳感器與微系統(tǒng);2016年12期

3 衛(wèi)麗華;朱鵬程;管致錦;;基于方向局部極值模式的圖像檢索算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2016年12期

4 黃梨力;;基于雙重采樣粒子濾波的目標(biāo)軌跡跟蹤研究[J];交通科技與經(jīng)濟(jì);2016年04期

5 劉萬(wàn)軍;董帥含;曲海成;;時(shí)空上下文抗遮擋視覺(jué)跟蹤[J];中國(guó)圖象圖形學(xué)報(bào);2016年08期

6 黃進(jìn);韓冬奇;陳毅能;田豐;王宏安;戴國(guó)忠;;混合現(xiàn)實(shí)中的人機(jī)交互綜述[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2016年06期

7 李亞杰;;圖像特征提取算法研究[J];科技廣場(chǎng);2016年05期

8 黃凱奇;陳曉棠;康運(yùn)鋒;譚鐵牛;;智能視頻監(jiān)控技術(shù)綜述[J];計(jì)算機(jī)學(xué)報(bào);2015年06期

，

本文編號(hào)：1792584