發(fā)布時(shí)間：2018-05-21 20:07

  本文選題：行人再識(shí)別 + 度量學(xué)習(xí)�。� 參考：《電子科技大學(xué)》2017年碩士論文

【摘要】：隨著計(jì)算機(jī)視覺(jué)和模式識(shí)別的發(fā)展,行人再識(shí)別已成為防止?jié)撛诒┝κ录�發(fā)生的有力工具。行人再識(shí)別是在非重疊視域中匹配同一行人目標(biāo)的過(guò)程。由于從不同視角采集的行人圖像分辨率低,存在光照、姿態(tài)、背景變化及遮擋等問(wèn)題,所以行人再識(shí)別一直是一項(xiàng)挑戰(zhàn)性的課題。為了克服這些問(wèn)題,行人再識(shí)別技術(shù)分別從兩個(gè)不同的方面著手:提取魯棒性的行人特征和學(xué)習(xí)合適的距離度量。在本論文中,我更多地關(guān)注后者。針對(duì)行人再識(shí)別問(wèn)題,本論文的主要工作如下:1.對(duì)行人再識(shí)別技術(shù)進(jìn)行概述。首先對(duì)行人再識(shí)別技術(shù)的背景、意義和發(fā)展歷史進(jìn)行了簡(jiǎn)單闡述。然后根據(jù)行人再識(shí)別技術(shù)的側(cè)重點(diǎn)不同分別從特征提取和度量學(xué)習(xí)兩個(gè)方面闡述了現(xiàn)有的行人再識(shí)別方法。2.研究基于核度量學(xué)習(xí)的行人再識(shí)別方法。核方法最大的優(yōu)勢(shì)就是在不知道具體的非線性映射函數(shù)的形式下,就可以將原始空間的數(shù)據(jù)向高維空間投影來(lái)提高分類能力。本文基于大間隔最近鄰(LMNN)、局部費(fèi)舍判別分析(LFDA)和Null Foley Sammon變換(NFST)提出了三種核度量學(xué)習(xí)方法。在三個(gè)具有挑戰(zhàn)性的行人再識(shí)別數(shù)據(jù)庫(kù)上的實(shí)驗(yàn)結(jié)果驗(yàn)證了核度量學(xué)習(xí)方法的有效性。3.提出基于非對(duì)稱幾何度量學(xué)習(xí)的行人再識(shí)別方法。它從幾何關(guān)系的角度針對(duì)每個(gè)特定的視角學(xué)習(xí)投影變換來(lái)提高對(duì)稱度量學(xué)習(xí)方法在行人再識(shí)別上的性能。對(duì)稱的度量學(xué)習(xí)方法對(duì)所有的視角學(xué)習(xí)單一的投影變換,然而這往往忽略了不同視角之間的差異性�；�于非對(duì)稱幾何度量學(xué)習(xí)的方法可以解決對(duì)稱度量學(xué)習(xí)在行人再識(shí)別上的上述問(wèn)題。在三個(gè)挑戰(zhàn)性的行人再識(shí)別數(shù)據(jù)庫(kù)上的識(shí)別性能,證明了其在行人再識(shí)別問(wèn)題上的有效性。
[Abstract]:With the development of computer vision and pattern recognition, pedestrian recognition has become a powerful tool to prevent potential violence. Pedestrian recognition is a process of matching the same pedestrian target in a non-overlapping horizon. Due to the low resolution of pedestrian images collected from different angles of view, there are problems such as illumination, posture, background change and occlusion, so pedestrian recognition is always a challenging task. In order to overcome these problems, the pedestrian recognition technique starts from two different aspects: extracting robust pedestrian features and learning appropriate distance metrics. In this paper, I pay more attention to the latter. The main work of this thesis is as follows: 1. The technology of pedestrian recognition is summarized. Firstly, the background, significance and development history of pedestrian recognition technology are briefly described. Then, according to the different emphases of pedestrian rerecognition technology, this paper expounds the existing pedestrian rerecognition methods from two aspects: feature extraction and measurement learning. A method of pedestrian rerecognition based on kernel metric learning is studied. The biggest advantage of the kernel method is that it can project the data of the original space to the high-dimensional space without knowing the specific nonlinear mapping function to improve the classification ability. In this paper, three kernel metric learning methods are proposed based on large interval nearest neighbor LMNNs, local Fisher discriminant analysis (LFDA) and Null Foley Sammon transform. Experimental results on three challenging pedestrian recognition databases verify the effectiveness of the kernel metric learning method. A method of pedestrian rerecognition based on asymmetric geometric metric learning is proposed. In order to improve the performance of the symmetric metric learning method in pedestrian recognition, the projection transformation is studied from the angle of geometric relation for each particular angle of view. Symmetric metric learning methods learn a single projection transformation for all visual angles, but this often ignores the differences between different perspectives. The method based on asymmetric geometric metric learning can solve the above problem of pedestrian rerecognition in symmetric metric learning. The recognition performance on three challenging pedestrian rerecognition databases proves its effectiveness in pedestrian rerecognition.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP181

【相似文獻(xiàn)】

相關(guān)博士學(xué)位論文 前1條

1 樊軍;高維二次度量回歸模型研究[D];北京交通大學(xué);2017年

相關(guān)碩士學(xué)位論文 前5條

1 楊淋淋;基于度量學(xué)習(xí)的行人再識(shí)別研究[D];電子科技大學(xué);2017年

2 向陽(yáng);非約束人臉識(shí)別中度量學(xué)習(xí)方法研究[D];北京郵電大學(xué);2016年

3 張葦寧;基于度量學(xué)習(xí)的行人再識(shí)別算法研究[D];遼寧大學(xué);2017年

4 趙玢琳;行人再辨識(shí)方法研究[D];北京郵電大學(xué);2017年

5 肖強(qiáng);具有標(biāo)量旗曲率的芬斯勒度量[D];浙江大學(xué);2016年

，

本文編號(hào)：1920600