本文選題：行人再識別　切入點：卷積神經(jīng)網(wǎng)絡(luò)　出處：《江蘇大學(xué)》2017年碩士論文

【摘要】：行人再識別作為公共場所視頻監(jiān)控中最重要的技術(shù)之一,受到了研究者的廣泛關(guān)注。目前,行人再識別方法普遍通過提取行人的顏色、紋理、形狀等低層特征來進行行人的區(qū)分,而行人作為一種非剛性對象,這些人工設(shè)定的特征對于行人的判斷并不是最好的,而且基于數(shù)值的低層特征缺乏語義表達能力,在行人再識別的實際應(yīng)用中不易被用戶所理解。此外,大多數(shù)行人再識別方法采取有監(jiān)督的學(xué)習(xí)方式,依賴于大量帶標(biāo)簽的訓(xùn)練數(shù)據(jù),而在實際應(yīng)用中,獲取關(guān)于每個行人的大量帶標(biāo)簽樣本圖像是不可能完成的任務(wù)。針對現(xiàn)有行人再識別中存在的這些問題,本文提出基于深度學(xué)習(xí)與屬性學(xué)習(xí)相結(jié)合的行人再識別方法,主要內(nèi)容如下:(1)提出基于無監(jiān)督卷積神經(jīng)網(wǎng)絡(luò)與行人屬性的行人再識別方法。該方法通過結(jié)合卷積神經(jīng)網(wǎng)絡(luò)的模型結(jié)構(gòu)和卷積自動編碼器的學(xué)習(xí)原理,無監(jiān)督地對行人圖像進行特征提取,避免了對帶標(biāo)簽訓(xùn)練樣本的依賴,同時通過這種數(shù)據(jù)驅(qū)動的特征學(xué)習(xí)方式獲得更具有代表性的行人特征,從而提高行人再識別的準(zhǔn)確率。在行人特征與行人類別間加入屬性層,通過對行人圖像的屬性判斷間接地進行行人類別的判斷,賦予了行人再識別方法更好的語義表達能力和實用價值。在VIPe R行人數(shù)據(jù)集上的實驗結(jié)果表明,與現(xiàn)階段所提方法相比,該方法能有效解決行人再識別中對帶標(biāo)簽數(shù)據(jù)的依賴問題和缺乏語義表達能力的問題,并有效提高了屬性分類器的準(zhǔn)確率。(2)提出基于無監(jiān)督卷積神經(jīng)網(wǎng)絡(luò)與層次屬性的行人再識別方法。該方法將行人圖像按身體部位劃分為互相重疊的若干分塊,對每個分塊針對性地提取特征并分配屬性分類器,有效降低了冗余信息對分類器造成的干擾,進一步提高了屬性分類器準(zhǔn)確率。引入層次屬性,利用粗、細粒度屬性來對行人進行區(qū)分,使得行人再識別方法更加符合人們的認(rèn)知規(guī)律,并能夠應(yīng)對不同程度行人描述時的再識別任務(wù)。在VIPe R行人數(shù)據(jù)集上,從多個方面驗證了所提方法的有效性,實驗結(jié)果表明該方法所取得的行人再識別準(zhǔn)確率高于現(xiàn)有其他算法,并且對于屬性缺失具有一定的容忍度。(3)設(shè)計并實現(xiàn)基于深度學(xué)習(xí)與屬性學(xué)習(xí)相結(jié)合的行人再識別原型系統(tǒng)。采用MATLAB實現(xiàn)了行人再識別系統(tǒng)的開發(fā)并設(shè)計了簡潔的GUI界面。系統(tǒng)包括有目標(biāo)行人圖像的再識別和無目標(biāo)行人圖像的再識別兩大功能模塊,主要包含目標(biāo)行人圖像輸入、行人層次屬性選擇、行人再識別和候選行人圖像展示等功能,驗證了本文所提行人再識別方法的可用性。
[Abstract]:Pedestrian recognition as one of the most important public places in video surveillance technology, has attracted much attention of researchers. At present, the pedestrian recognition method by extracting common pedestrian color, texture, shape and other features to distinguish the low layer of pedestrians, and as a kind of non rigid object, the artificial set of features for the and determine the pedestrian is not the best, but the lack of low level features numerical semantic expression ability based on the practical application in the recognition of pedestrians are not easy to be understood by users. In addition, most of the pedestrian recognition method adopts supervised learning method, relies on a large number of training data with the label, but in practical application. For each pedestrian plenty of labeled sample image is an impossible task. According to the existing pedestrian recognition of these problems, this paper based on deep learning and attributes Recognition method of pedestrian combination of study, the main contents are as follows: (1) proposed unsupervised convolutional neural network and pedestrian pedestrian recognition method based on attribute. This method by learning principle combined with convolutional neural network model structure and automatic convolution encoder, the feature extraction of pedestrian images without supervision, to avoid the dependence on the labeled training samples, and feature driven by this data learning way of obtaining pedestrian characteristics more representative, so as to improve the accuracy of pedestrian recognition. The pedestrian characteristics and pedestrian categories added attribute layer, judge indirectly by category judgment through the attribute of the pedestrian pedestrian image, expression ability and practical the semantic value gives better. Then pedestrian recognition method in VIPe R pedestrian dataset. The experimental results show that, compared with the stage of the proposed method, this method can effectively To solve the problem of dependence on labeled data and the lack of semantic expression ability of re recognition of pedestrians, and effectively improve the accuracy of attribute classifiers. (2) proposed unsupervised convolutional neural networks with different attributes and pedestrian recognition method based on this method. The pedestrian image according to parts of the body are divided into several overlapping points for each block, the block to extract features and distribution of attribute classifier, effectively reduce the interference of redundant information to the classifier caused, to further improve the classifier accuracy. The attribute level attribute, using coarse and fine granularity attribute to distinguish pedestrian, pedestrian recognition method makes more in line with the cognition of the people, and to cope with the different degree of pedestrian description recognition task. In the VIPe R pedestrian dataset, the effectiveness of the proposed method are verified from many aspects, the experimental results show that the The method of pedestrian recognition accuracy than other existing algorithms, and for the missing attribute has a certain tolerance. (3) the design and implementation of pedestrian deep learning and attribute based learning combined recognition prototype system. Using the MATLAB to realize the development of pedestrian recognition system and design a simple GUI interface. No target recognition and image recognition of pedestrians two major functional modules of the system include target pedestrian images, including pedestrian target image input, the pedestrian level attribute selection, pedestrian recognition and candidate pedestrian image display and other functions, to verify the availability of recognition method this paper submitted for people.

【學(xué)位授予單位】：江蘇大學(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】

相關(guān)期刊論文 前3條

1 程艷;楊業(yè)全;趙軍;;提升視頻監(jiān)控系統(tǒng)應(yīng)用效能之策略研究[J];湖北警官學(xué)院學(xué)報;2015年04期

2 曲建嶺;杜辰飛;邸亞洲;高峰;郭超然;;深度自動編碼器的研究與展望[J];計算機與現(xiàn)代化;2014年08期

3 ;Tracking multiple people under occlusion and across cameras using probabilistic models[J];Journal of Zhejiang University(Science A:An International Applied Physics & Engineering Journal);2009年07期

，

本文編號：1708570