【摘要】：生物識(shí)別技術(shù)是計(jì)算機(jī)視覺(jué)領(lǐng)域一個(gè)前沿的研究課題。在眾多的生物特征之中,步態(tài)具有可遠(yuǎn)程獲取、魯棒性強(qiáng)、安全性強(qiáng)等優(yōu)勢(shì)。因此,在“以人為中心”的現(xiàn)代智能監(jiān)控系統(tǒng)中,步態(tài)識(shí)別技術(shù)獲得了越來(lái)越多的關(guān)注。然而此問(wèn)題存在著眾多挑戰(zhàn),比如相同目標(biāo)因不同視角、穿戴和行走速度帶來(lái)的類(lèi)內(nèi)差異太大,以及不同目標(biāo)之間的形態(tài)相似性帶來(lái)的類(lèi)間語(yǔ)義模糊等。目前的步態(tài)識(shí)別技術(shù)大多基于人工視覺(jué)特征來(lái)進(jìn)行模型匹配,但是傳統(tǒng)的人工特征已經(jīng)無(wú)法滿足步態(tài)精細(xì)識(shí)別的需求,所以很難打破特征提取和特征表示的瓶頸。在本文中,我們圍繞基于深度學(xué)習(xí)的步態(tài)識(shí)別問(wèn)題,提出了一系列新模型和新方法。首先,我們?cè)O(shè)計(jì)了一個(gè)基于深度學(xué)習(xí)的步態(tài)識(shí)別技術(shù)框架。為了克服現(xiàn)有步態(tài)數(shù)據(jù)庫(kù)樣本容量小以及深度學(xué)習(xí)訓(xùn)練速度慢的挑戰(zhàn),我們將原始的步態(tài)序列進(jìn)行融合,計(jì)算其步態(tài)能量圖作為卷積神經(jīng)網(wǎng)絡(luò)的輸入來(lái)對(duì)預(yù)訓(xùn)練的網(wǎng)絡(luò)進(jìn)行微調(diào)。然后,我們提出了基于Siamese神經(jīng)網(wǎng)絡(luò)的步態(tài)識(shí)別技術(shù)。該技術(shù)借助深度神經(jīng)網(wǎng)絡(luò)的視覺(jué)特征學(xué)習(xí)能力與Siamese結(jié)構(gòu)的距離度量學(xué)習(xí)特性,有效解決了深度學(xué)習(xí)訓(xùn)練數(shù)據(jù)量不足以及分類(lèi)與識(shí)別任務(wù)的領(lǐng)域鴻溝問(wèn)題。最后,我們通過(guò)聯(lián)合步態(tài)序列的三維卷積特征和Siamese結(jié)構(gòu)在三維空間進(jìn)行特征度量學(xué)習(xí)。該方法可以從連續(xù)的周期性步態(tài)序列中捕捉空間維度和時(shí)間維度的信息,進(jìn)一步提高步態(tài)識(shí)別的準(zhǔn)確率和實(shí)用性。經(jīng)實(shí)驗(yàn)驗(yàn)證,本文提出的方法在步態(tài)屬性分類(lèi)和身份識(shí)別中都取得了理想的結(jié)果,特別是在身份識(shí)別任務(wù)中,在目前世界上最大的步態(tài)數(shù)據(jù)庫(kù)中,本文算法相比已有最好方法在正確識(shí)別率方面平均提高了5%。
[Abstract]:Biometrics is a frontier research topic in the field of computer vision. Among the many biological features, gait has the advantages of remote acquisition, robustness and security. Therefore, gait recognition technology has gained more and more attention in the modern intelligent monitoring system. However, there are many challenges to this problem, such as the same target is different from different angles of view, the intra-class differences caused by wearing and walking speed are too big, and the semantic ambiguity between classes caused by the morphological similarity between different targets and so on. Most of the current gait recognition techniques are based on artificial visual features for model matching, but the traditional artificial features can no longer meet the needs of fine gait recognition, so it is difficult to break the bottleneck of feature extraction and feature representation. In this paper, we propose a series of new models and methods for gait recognition based on deep learning. Firstly, we design a gait recognition framework based on deep learning. In order to overcome the challenge of small sample size and slow training speed in the existing gait database, we fuse the original gait sequences. The gait energy diagram is calculated as the input of the convolutional neural network to fine-tune the pretrained network. Then, we propose a gait recognition technique based on Siamese neural network. With the help of the visual feature learning ability of the deep neural network and the distance metric learning characteristic of the Siamese structure, this technique effectively solves the problem of insufficient data amount of in-depth learning training and the domain gap between classification and recognition tasks. Finally, we study the feature metrics in 3D space by combining the 3D convolution features of gait sequences and the Siamese structure. This method can capture the information of spatial dimension and time dimension from continuous periodic gait sequences and further improve the accuracy and practicability of gait recognition. Experimental results show that the proposed method has achieved ideal results in gait attribute classification and identification, especially in the task of identification and in the world's largest gait database. Compared with the best method, the algorithm improves the correct recognition rate by an average of 5%.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TP391.41;TP181

【引證文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 陳春利;基于集成深度學(xué)習(xí)的雷達(dá)信號(hào)識(shí)別方法研究[D];西南交通大學(xué);2018年

，

本文編號(hào)：2312871