本文選題：局部特征提取　切入點：支持向量機　出處：《中國科學(xué)院大學(xué)(中國科學(xué)院光電技術(shù)研究所)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：目標(biāo)檢測與跟蹤作為計算機視覺研究領(lǐng)域的一個重要組成部分,未來有望廣泛應(yīng)用于運動的識別、自動監(jiān)督、視頻檢索、人機交互等諸多現(xiàn)代技術(shù)領(lǐng)域。而傳統(tǒng)的目標(biāo)檢測與跟蹤算法一般只采用圖像底層的視覺特征來構(gòu)建目標(biāo)描述子,獲得目標(biāo)外觀的描述,來進行目標(biāo)檢測與跟蹤;或者通過簡單的背景建模方式來區(qū)分前景和背景,從而獲取目標(biāo)的位置信息,實現(xiàn)目標(biāo)的檢測與跟蹤。然而在實際過程中,除了存在目標(biāo)自身姿態(tài)、尺度、旋轉(zhuǎn)、平移變化,還存在光照變化、復(fù)雜背景、目標(biāo)遮擋等挑戰(zhàn)。由于底層特征對這些變化不具有不變性,無法精確的描述目標(biāo),造成跟蹤器失效。因為局部特征對目標(biāo)檢測與跟蹤過程中的變換具有良好的不變性,所以通過提取目標(biāo)的局部特征,構(gòu)建魯棒的目標(biāo)描述子并結(jié)合魯棒的目標(biāo)檢測與跟蹤框架成為了目標(biāo)檢測與跟蹤技術(shù)研究中的一個熱點。在目標(biāo)檢測方面,首先分析了HOG-PCA描述子和支持向量機目標(biāo)檢測方法的優(yōu)勢與不足。針對在提取HOG局部特征時采用傳統(tǒng)四象限組合成塊方式,構(gòu)建的目標(biāo)描述子不能精確的描述目標(biāo),并對后續(xù)提取特征主元沒有優(yōu)勢的不足,提出了一種改進HOG-PCA特征描述子的方法,在提取HOG特征時采用極坐標(biāo)組合塊方法代替?zhèn)鹘y(tǒng)四象限的方法,構(gòu)建能更精確表示目標(biāo)的描述子。另一方面通過循環(huán)采樣的方式代替?zhèn)鹘y(tǒng)的隨機采樣方式,構(gòu)建用于SVM訓(xùn)練的正負(fù)樣本,使訓(xùn)練器訓(xùn)練的結(jié)果更加精確。通過提取正負(fù)樣本改進后的HOG-PCA描述子,進行主成分分析,然后作為樣本數(shù)據(jù),用于支持向量機分類器的訓(xùn)練,最后將訓(xùn)練好的分類器用于目標(biāo)的檢測。在目標(biāo)跟蹤方面,同樣從提取目標(biāo)的局部特征,構(gòu)建魯棒的目標(biāo)描述子出發(fā),針對傳統(tǒng)的空時上下文跟蹤器中只使用高斯加權(quán)的底層灰度特征來獲得目標(biāo)的特征描述,在復(fù)雜場景下,不能獲到魯棒跟蹤結(jié)果的不足。本文通過提取目標(biāo)圖像的局部圓域混合塊LBP特征,構(gòu)造圖像的響應(yīng)圖,獲得了目標(biāo)的外觀描述,然后在貝葉斯框架下對目標(biāo)和它的局部上下文區(qū)域的時空關(guān)系進行建模,提出了一種利用目標(biāo)周圍上下文視覺顯著信息進行跟蹤的算法。本文在目標(biāo)檢測方面使用了INRIA行人數(shù)據(jù)集來對改進后HOG-PCA特征的SVM目標(biāo)檢測方法進行了全面的測試,將其與原來的算法進行了比對,實驗結(jié)果表明改進后的算法能夠明顯的降低目標(biāo)的誤檢率。在目標(biāo)跟蹤方面使用了大量的經(jīng)典跟蹤視頻集對算法進行了全面的測試,也加入了另外三種經(jīng)典跟蹤算法的結(jié)果來進行比較與分析,實驗表明本文算法的性能要勝于其他跟蹤算法。最后,對本文的研究內(nèi)容進行了全面的總結(jié),并為后續(xù)的研究工作提供了思路。
[Abstract]:As an important part of computer vision research, target detection and tracking is expected to be widely used in motion recognition, automatic monitoring and video retrieval in the future. The traditional target detection and tracking algorithms only use the visual features of the bottom layer of the image to construct the object descriptor and obtain the description of the appearance of the target to detect and track the target. Or it can distinguish the foreground and background by simple background modeling method, so as to obtain the position information of the target, and realize the detection and tracking of the target. However, in the actual process, there are not only the changes of the target's own attitude, scale, rotation and translation, but also the change of the target's attitude, scale, rotation and translation. There are also challenges such as illumination changes, complex backgrounds, object occlusion, and so on. Because the underlying features are not invariant to these changes, it is impossible to accurately describe the target. Because the local feature has good invariance to the transformation in the process of target detection and tracking, so by extracting the local feature of the target, Constructing robust target descriptor and combining robust target detection and tracking framework has become a hot topic in the research of target detection and tracking technology. Firstly, the advantages and disadvantages of HOG-PCA descriptor and support vector machine (SVM) are analyzed. In order to extract the local features of HOG, the target descriptor can not accurately describe the target by using the traditional four-quadrant combination method. In this paper, an improved method of HOG-PCA feature descriptor is proposed, in which polar coordinate combination block method is used to replace the traditional four-quadrant method in HOG feature extraction. On the other hand, instead of traditional random sampling, positive and negative samples for SVM training are constructed. By extracting the improved HOG-PCA descriptor of positive and negative samples, the principal component analysis (PCA) is used as sample data to train the classifier of support vector machine (SVM). Finally, the trained classifier is used for target detection. In the aspect of target tracking, a robust target descriptor is constructed by extracting the local features of the target. In the traditional space-time context tracker, only Gao Si's weighted low-level gray features are used to obtain the feature description of the target. The result of robust tracking can not be obtained. In this paper, by extracting the local circular region mixed block LBP features of the target image, the response graph of the image is constructed, and the appearance description of the target is obtained. Then the spatiotemporal relationship between the target and its local context is modeled under the Bayesian framework. In this paper, we propose a tracking algorithm using visual salient information about the context around the target. In this paper, we use INRIA pedestrian data set to test the improved SVM target detection method based on HOG-PCA features. Compared with the original algorithm, the experimental results show that the improved algorithm can significantly reduce the false detection rate of the target. In the aspect of target tracking, a large number of classical tracking video sets are used to test the algorithm. The results of the other three classical tracking algorithms are compared and analyzed. The experimental results show that the performance of this algorithm is better than that of other tracking algorithms. Finally, the research content of this paper is summarized comprehensively. It also provides the train of thought for the following research work.
【學(xué)位授予單位】：中國科學(xué)院大學(xué)(中國科學(xué)院光電技術(shù)研究所)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前3條

1 宿德志;王坤;王玉良;趙文飛;;基于SURF算法和Kalman預(yù)測的運動目標(biāo)跟蹤[J];海軍航空工程學(xué)院學(xué)報;2013年04期

2 劉晨光;劉家鋒;黃劍華;唐降龍;;基于多特征融合的分塊采樣粒子濾波算法在人體姿態(tài)跟蹤中的應(yīng)用[J];計算機研究與發(fā)展;2011年12期

3 仝小敏;張艷寧;楊濤;;基于增量子空間自適應(yīng)決策的目標(biāo)跟蹤[J];自動化學(xué)報;2011年12期

，

本文編號：1591865