本文選題：目標(biāo)跟蹤　切入點(diǎn)：深度信息　出處：《哈爾濱工業(yè)大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：視覺目標(biāo)跟蹤(Visual Object Tracking)在智能監(jiān)控、人機(jī)交互、無人駕駛、虛擬現(xiàn)實(shí)等領(lǐng)域有非常重要的應(yīng)用價(jià)值,一直以來都是計(jì)算機(jī)視覺領(lǐng)域的研究熱點(diǎn)。近幾年,相關(guān)濾波跟蹤算法和基于深度學(xué)習(xí)的跟蹤算法的提出顯著提升了跟蹤速度和精度。但是在目標(biāo)被遮擋、目標(biāo)尺度變化或處于復(fù)雜背景等情況下,尤其是目標(biāo)被長時間或者嚴(yán)重遮擋的時候,如何準(zhǔn)確跟蹤目標(biāo)仍是困擾著研究者們的難題。遮擋是三維世界投影到二維平面的信息損失導(dǎo)致的,因此出現(xiàn)一些使用深度信息的二維或三維跟蹤方法,借助三維空間結(jié)構(gòu)來幫助解決這些難題,并取得了一定的進(jìn)展。由于近幾年深度傳感器精度的提升和價(jià)格的下降,使得深度信息的獲取變得容易。此外還有無人機(jī)、機(jī)器人、無人駕駛汽車等越來越多的設(shè)備攜帶有深度傳感器,因此在與這些設(shè)備相關(guān)的應(yīng)用場景下使用深度信息協(xié)助目標(biāo)跟蹤有重要的研究和應(yīng)用價(jià)值。目前基于深度信息的跟蹤算法分為兩類,其中二維跟蹤方法不能有效的使用深度信息,沒有把深度信息與已有的跟蹤算法深度融合。而三維跟蹤方法由于缺乏比較成熟的三維特征提取技術(shù),目標(biāo)的三維表觀模型并不魯棒,進(jìn)而影響其跟蹤效果。本文針對上述問題提出使用自適應(yīng)量化的深度信息,根據(jù)不同場景建立相適應(yīng)的分層結(jié)構(gòu),一方面過濾前景和背景信息減少跟蹤的干擾因素,結(jié)合成熟的圖像特征提取技術(shù),包括HOG特征和顏色屬性直方圖特征等,建立目標(biāo)魯棒的目標(biāo)表觀模型;另一方面這樣的分層結(jié)構(gòu)簡化了深度信息的使用方法,使得處理目標(biāo)尺度變化以及檢測遮擋更為容易。在分層結(jié)構(gòu)的基礎(chǔ)上,提出在取樣之前完成目標(biāo)尺度估計(jì)的策略,以及快速檢測遮擋的策略。結(jié)合核相關(guān)濾波(Kernel Correlation Filter)跟蹤算法實(shí)現(xiàn)了使用二維表觀模型在空間結(jié)構(gòu)下的跟蹤方法,能夠有效應(yīng)對遮擋和處理目標(biāo)尺度變化。本文參加普林斯頓跟蹤測評,該測評的數(shù)據(jù)集有100個跟蹤視頻序列,包含多種目標(biāo)、多種遮擋情況和多個不同場景。最終實(shí)現(xiàn)的跟蹤算法在基于RGB-D圖像分組中排名第四,驗(yàn)證了所提算法的有效性。
[Abstract]:Visual Object tracking has very important application value in the fields of intelligent monitoring, human-computer interaction, driverless, virtual reality and so on, and has always been the research hotspot in the field of computer vision. Correlation filter tracking algorithm and depth learning based tracking algorithm can improve the tracking speed and precision significantly. However, when the target is occluded, the target scale changes or is in a complex background, etc. Especially when the target is occluded for a long time or severely, how to track the target accurately is still a difficult problem for researchers. Occlusion is caused by the loss of information projected into the two-dimensional plane by the three-dimensional world. Therefore, some 2D or 3D tracking methods using depth information have been developed to help solve these problems with the help of three-dimensional spatial structure, and some progress has been made. It makes it easier to access depth information. And more and more devices, such as drones, robots, driverless cars, are carrying depth sensors. Therefore, using depth information to assist target tracking in application scenarios related to these devices has important research and application value. At present, depth information based tracking algorithms can be divided into two categories. The 2D tracking method can not use depth information effectively and does not fuse the depth information with the existing tracking algorithms. However, the 3D tracking method lacks the mature 3D feature extraction technology. The 3D apparent model of the target is not robust, which affects the tracking effect. In this paper, the adaptive quantization depth information is used to establish the appropriate hierarchical structure according to different scenes. On the one hand, filtering foreground and background information to reduce the interference factors of tracking, combined with mature image feature extraction technology, including HOG features and color attributes histogram features, to establish a robust target model; On the other hand, this kind of layered structure simplifies the use of depth information, makes it easier to process the change of target scale and detect occlusion. On the basis of stratified structure, the strategy of completing target scale estimation before sampling is proposed. Combined with Kernel Correlation filter (Kernel Correlation filter) tracking algorithm, the tracking method using two-dimensional apparent model in spatial structure is realized. This paper participates in the Princeton tracking Evaluation, which has 100 tracking video sequences, including a variety of targets. Finally, the tracking algorithm is ranked 4th in the image grouping based on RGB-D, which verifies the effectiveness of the proposed algorithm.
【學(xué)位授予單位】：哈爾濱工業(yè)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 趙海楠;視覺目標(biāo)跟蹤中表觀建模方法研究[D];哈爾濱工業(yè)大學(xué);2016年

，

本文編號：1602741