本文選題：步態(tài)識(shí)別 + 確定學(xué)習(xí)　； 參考：《華南理工大學(xué)》2012年碩士論文

【摘要】：隨著信息技術(shù)的不斷發(fā)展，計(jì)算機(jī)可以更加快速、更加有效的為我們服務(wù)，尤其是在處理一些高階次、計(jì)算量很大的科學(xué)問(wèn)題上，計(jì)算機(jī)的性能直接影響問(wèn)題解決的方式。當(dāng)今計(jì)算機(jī)的處理水平已經(jīng)不局限于用于物理上的內(nèi)存擴(kuò)展和處理器速度的提高，，類(lèi)型多樣的并行處理體系得到應(yīng)用。而并行計(jì)算的應(yīng)用可以在處理器能力沒(méi)有質(zhì)的飛躍的前提下，大幅度提高計(jì)算機(jī)的性能。其原理是將一個(gè)計(jì)算任務(wù)分配到不同的進(jìn)程中去，同時(shí)處理，從而加快計(jì)算的速度，提高解決問(wèn)題的效率，與很多科學(xué)問(wèn)題有很好的結(jié)合能力。 步態(tài)識(shí)別技術(shù)可以根據(jù)人體的步態(tài)特征，在遠(yuǎn)距離、具有隱蔽性的前提下，識(shí)別出個(gè)體的身份，這在當(dāng)今存在越來(lái)越多需要對(duì)人的身份進(jìn)行識(shí)別的場(chǎng)合的背景下，具有重要意義�，F(xiàn)在的步態(tài)識(shí)別技術(shù)是基于行為特征的，對(duì)包含個(gè)體特征的圖像序列進(jìn)行預(yù)處理、檢測(cè)和特征提取，然后才可以進(jìn)行識(shí)別。由于人體的行為特征非常復(fù)雜，進(jìn)行建模時(shí)包含很多未知部分。這時(shí)，確定學(xué)習(xí)理論的應(yīng)用很好的解決了這個(gè)問(wèn)題。確定學(xué)習(xí)理論是基于RBF神經(jīng)網(wǎng)絡(luò)的在未知?jiǎng)討B(tài)環(huán)境下，可以對(duì)系統(tǒng)局部動(dòng)態(tài)進(jìn)行準(zhǔn)確逼近的新理論。在辨識(shí)出來(lái)步態(tài)的動(dòng)態(tài)特征之后存儲(chǔ)于常值神經(jīng)網(wǎng)絡(luò)，然后利用已存儲(chǔ)的模式對(duì)步態(tài)特征進(jìn)行快速準(zhǔn)確識(shí)別。 本文主要介紹了確定學(xué)習(xí)理論在步態(tài)特征識(shí)別中的實(shí)際應(yīng)用。為了加速識(shí)別過(guò)程，提高識(shí)別效率，在步態(tài)識(shí)別的具體應(yīng)用中，應(yīng)用了并行計(jì)算的實(shí)現(xiàn)方式。在并行的硬件平臺(tái)上，構(gòu)造并行的識(shí)別算法，并且在多核的平臺(tái)上實(shí)現(xiàn)了步態(tài)識(shí)別的并行程序設(shè)計(jì)，分析了程序的性能。最后為了處理過(guò)程的直觀(guān)性和方便性，分別用基于C++的MFC框架和matlab GUI建立了步態(tài)特征提取和識(shí)別的系統(tǒng)界面，展示了識(shí)別的快速性和有效性。
[Abstract]:With the continuous development of information technology, computers can serve us more quickly and effectively, especially in dealing with some scientific problems of high order and large amount of computation. The performance of computers directly affects the way to solve the problems. Nowadays, the processing level of computers is no longer limited to physical memory expansion and processor speed improvement. Parallel processing systems of various types have been applied. Parallel computing applications can greatly improve the performance of computers without a qualitative leap in processor power. The principle is to assign a computing task to different processes and deal with it at the same time, so as to speed up the calculation, improve the efficiency of solving problems, and have a good ability to combine with many scientific problems. Gait recognition technology can recognize the identity of individuals on the premise of distance and concealment according to the gait characteristics of human body. It is of great significance. The current gait recognition technology is based on behavioral features. The image sequences containing individual features are preprocessed, detected and feature extracted before recognition can be carried out. Due to the complexity of human behavior, modeling contains many unknown parts. At this time, the application of deterministic learning theory solves this problem very well. Deterministic learning theory is a new theory based on RBF neural network which can accurately approximate the local dynamics of the system in unknown dynamic environment. After the gait dynamic features are identified, they are stored in the constant neural network, and the stored patterns are used to identify the gait features quickly and accurately. This paper mainly introduces the practical application of deterministic learning theory in gait feature recognition. In order to accelerate the recognition process and improve the recognition efficiency, parallel computing is applied in gait recognition. The parallel recognition algorithm is constructed on the parallel hardware platform, and the parallel program design for gait recognition is implemented on the multi-core platform, and the performance of the program is analyzed. Finally, in order to deal with the intuitiveness and convenience of the process, the system interface of gait feature extraction and recognition is established by using MFC framework based on C and matlab GUI, respectively, which shows the rapidity and validity of recognition.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類(lèi)號(hào)】：TP391.41;TP338.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 王江濤;陳得寶;鄒峰;;一種OpenCV,VFW及VCM相結(jié)合的實(shí)時(shí)視頻處理框架[J];電視技術(shù);2010年06期

2 張敏園;張世功;;利用MATLAB制作不確定度合成的GUI程序[J];大學(xué)物理實(shí)驗(yàn);2010年04期

3 李鶴;侯海翔;姜躍;廖小飛;金海;;面向多虛擬機(jī)的分布式存儲(chǔ)系統(tǒng)[J];計(jì)算機(jī)科學(xué)與探索;2011年07期

4 姜攀;;并行計(jì)算機(jī)的比較分析[J];軟件導(dǎo)刊;2010年06期

5 劉磊;李?lèi)?ài)霞;陳生潭;;步態(tài)識(shí)別預(yù)處理方法綜述[J];網(wǎng)絡(luò)安全技術(shù)與應(yīng)用;2008年01期

6 王玉林;葛蕾;李艷斌;;新型界面開(kāi)發(fā)工具:MATLAB/GUI[J];無(wú)線(xiàn)電通信技術(shù);2008年06期

相關(guān)博士學(xué)位論文 前2條

1 蔣江;異構(gòu)集群系統(tǒng)中基于進(jìn)程遷移機(jī)制的負(fù)載平衡算法的研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2002年

2 武華北;混合并行計(jì)算環(huán)境多級(jí)并行化編程模式的研究[D];天津大學(xué);2009年

相關(guān)碩士學(xué)位論文 前5條

1 張恒;基于輪廓的步態(tài)識(shí)別[D];南京信息工程大學(xué);2011年

2 張工;基于VC++的DPIV圖像后處理軟件系統(tǒng)[D];大連理工大學(xué);2006年

3 張媛;步態(tài)識(shí)別中幾個(gè)關(guān)鍵技術(shù)的研究[D];西安理工大學(xué);2007年

4 阮宇慧;步態(tài)識(shí)別的算法研究和系統(tǒng)實(shí)現(xiàn)[D];北京交通大學(xué);2008年

5 虞永方;基于步態(tài)的身份識(shí)別的算法實(shí)現(xiàn)[D];吉林大學(xué);2009年

本文編號(hào)：1989371