本文關(guān)鍵詞：基于卷積神經(jīng)網(wǎng)絡(luò)的行人重識別算法　出處：《華東師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 行人重識別 卷積神經(jīng)網(wǎng)絡(luò) 深度學(xué)習(xí) 度量學(xué)習(xí) 相似度度量

【摘要】：隨著監(jiān)控攝像頭在各領(lǐng)域的大量應(yīng)用,傳統(tǒng)的人工監(jiān)控方法無法應(yīng)對由此產(chǎn)生的海量監(jiān)控視頻。行人重識別是指在多臺攝像機監(jiān)控下進行行人匹配,即給定一個行人目標(biāo),在多臺不同位置的攝像機不同時刻拍攝的視頻中找到該目標(biāo)。行人重識別(person re-identification)技術(shù)是智能視頻分析、視頻監(jiān)控、人機交互等諸多領(lǐng)域的核心技術(shù),已經(jīng)成為計算機視覺領(lǐng)域的研究熱點。但是因為光照、視角、姿勢、遮擋和分辨率等因素的影響,使得行人重識別技術(shù)存在很大的挑戰(zhàn)性。行人重識別通常主要包含兩個步驟,首先設(shè)計有效的描述行人的特征,然后通過度量學(xué)習(xí)算法進行相似性度量。傳統(tǒng)的行人重識別方法依靠人工設(shè)計的特征,但由于同一個行人在不同圖像中可能有很大差異,而不同的行人又可能看起來很相像,使得這些手工特征很難應(yīng)用到復(fù)雜的現(xiàn)實環(huán)境中。深度學(xué)習(xí)目前已經(jīng)成功地應(yīng)用在計算機視覺的很多領(lǐng)域,如手寫字符識別、目標(biāo)檢測、圖像分類、人臉識別等,在行人重識別領(lǐng)域也有一定的研究。本文采用深度學(xué)習(xí)方法對行人重識別進行研究,主要研究內(nèi)容包括:1、基于卷積神經(jīng)網(wǎng)絡(luò)中的分類模型的行人重識別研究。不同于常用的相似性度量中的對比損失和三重?fù)p失函數(shù),我們用SoftMax損失訓(xùn)練網(wǎng)絡(luò)。首先對ImageNet數(shù)據(jù)庫上預(yù)訓(xùn)練好的AlexNet用行人數(shù)據(jù)庫進行微調(diào)(Fine-Tuning),用該網(wǎng)絡(luò)提取行人特征,并采用目前效果較好的度量學(xué)習(xí)方法進行識別。其次設(shè)計了一個行人分類專用的卷積神經(jīng)網(wǎng)絡(luò),用于提取行人特征,然后用度量學(xué)習(xí)算法進行行人重識別。2、提出了一種改進的Siamese結(jié)構(gòu)的基于深度卷積神經(jīng)網(wǎng)絡(luò)的行人重識別模型。訓(xùn)練時結(jié)合了分類和相似性度量,從而增大類間距離,縮小類內(nèi)距離,提取出行人的有效特征,然后再進一步用度量學(xué)習(xí)算法進行相似度度量。本文在三個公開的行人重識別數(shù)據(jù)集上進行實驗,采用累積匹配特征(Cumulative Matching Characteristic,CMC)曲線對實驗結(jié)果進行驗證,與其他行人重識別算法進行對比試驗,我們的模型優(yōu)于大部分現(xiàn)有模型。
[Abstract]:With a large number of applications of surveillance cameras in various fields, the traditional manual monitoring methods can not cope with the resulting mass of surveillance video. Pedestrian recognition refers to pedestrian matching under the surveillance of multiple cameras. Given a pedestrian target. The target is found in videos taken at different times by cameras in different locations. Pedestrian re-identification is intelligent video analysis. Video surveillance, human-computer interaction and other fields of core technology, has become a research hotspot in the field of computer vision, but due to lighting, perspective, posture, occlusion and resolution and other factors. Pedestrian recognition technology has a great challenge. Pedestrian recognition usually consists of two steps: first, design an effective description of pedestrian characteristics. Traditional pedestrian recognition methods rely on artificial features, but the same pedestrian may be very different in different images. However, different pedestrians may look very similar, which makes it difficult to apply these manual features to complex real environment. Depth learning has been successfully applied in many fields of computer vision. Such as handwritten character recognition, target detection, image classification, face recognition, there are also some research in the field of pedestrian recognition. The main research contents include: 1, pedestrian recognition based on classification model in convolutional neural network, which is different from the contrast loss and triple loss function in similarity measurement. We use the SoftMax loss training network. Firstly, we fine-tune the pre-trained AlexNet using pedestrian database on the ImageNet database. The network is used to extract pedestrian features, and the current effective metric learning method is used to identify them. Secondly, a special convolutional neural network for pedestrian classification is designed to extract pedestrian features. Then the measurement learning algorithm is used for pedestrian recognition. 2. An improved Siamese structure pedestrian recognition model based on deep convolution neural network is proposed. The training combines classification and similarity measurement to increase inter-class distance and reduce intra-class distance. The effective features of travelers are extracted, and then the similarity is measured using metric learning algorithm. Experiments are carried out on three published pedestrian recognition data sets. The experimental results were verified by cumulative Matching character curve. Compared with other pedestrian recognition algorithms, our model is superior to most existing models.
【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP183

【參考文獻】

相關(guān)期刊論文 前2條

1 張耿寧;王家寶;李陽;苗壯;張亞非;李航;;基于特征融合與核局部Fisher判別分析的行人重識別[J];計算機應(yīng)用;2016年09期

2 陳瑩;霍中花;;多方向顯著性權(quán)值學(xué)習(xí)的行人再識別[J];中國圖象圖形學(xué)報;2015年12期

，

本文編號：1432830