本文選題：步態(tài)識(shí)別 + OpenCV��； 參考：《哈爾濱商業(yè)大學(xué)》2017年碩士論文

【摘要】：隨著計(jì)算機(jī)視覺技術(shù)的快速發(fā)展,人們對(duì)安全的需求與日俱增,生物特征識(shí)別,作為對(duì)安全場(chǎng)合常用的身份鑒別技術(shù),受到廣泛的關(guān)注與研究。人臉、指紋等生物特征不僅要求近距離接觸攝像裝置,而且識(shí)別技術(shù)實(shí)現(xiàn)成本較高。而步態(tài)識(shí)別,具有非接觸性、隱蔽性等特點(diǎn),克服了傳統(tǒng)的生物特征識(shí)別需要高分辨率圖像的缺陷。本文基于OpenCV開源函數(shù)庫(kù),以步態(tài)識(shí)別在門禁系統(tǒng)中的應(yīng)用為前提,利用C與C++(基于MFC)作為開發(fā)工具,開發(fā)實(shí)現(xiàn)了一套完整的步態(tài)識(shí)別系統(tǒng),并深入研究步態(tài)識(shí)別中的拒識(shí)算法。本文設(shè)計(jì)一套完整的步態(tài)識(shí)別技術(shù)方案,該方案以Matlab為開發(fā)工具,對(duì)中科院自動(dòng)化所提供的大型步態(tài)數(shù)據(jù)庫(kù)CASIA-B中的樣本進(jìn)行測(cè)試,試驗(yàn)結(jié)果表明,該步態(tài)識(shí)別技術(shù)方案達(dá)到了理想的識(shí)別率。在此基礎(chǔ)上,完成以下三個(gè)方面的工作:第一、利用C與C++實(shí)現(xiàn)整個(gè)步態(tài)識(shí)別技術(shù),形成可以獨(dú)立使用的各個(gè)功能模塊;第二、搭建完整的步態(tài)圖像采集環(huán)境。該圖像采集環(huán)境由攝像頭模塊、單色背景和燈光組成,形成一套固定的采集環(huán)境,減少外部因素產(chǎn)生的噪聲;第三、提出一種背景檢測(cè)與去除算法及拒識(shí)算法。添加攝像頭模塊后,由于實(shí)際環(huán)境的噪聲干擾,在圖像預(yù)處理階段會(huì)產(chǎn)生大量的噪聲(陰影),不利于特征提取,將圖像轉(zhuǎn)換到Y(jié)CrCb顏色空間中,將目標(biāo)圖片與背景圖片的Y、Cr、Cb通道求差,通過設(shè)定的幀差閾值找到陰影位置并實(shí)現(xiàn)陰影去除。另外,由于門禁系統(tǒng)在實(shí)際應(yīng)用中不僅需要滿足較高的識(shí)別率,還需有拒識(shí)功能,即不僅能準(zhǔn)確識(shí)別訓(xùn)練樣本庫(kù)中的真實(shí)樣本,還能拒絕識(shí)別不屬于訓(xùn)練樣本類的虛假樣本。因此,本文對(duì)步態(tài)識(shí)別中拒識(shí)模塊展開研究,提出一種基于極值尋優(yōu)的拒識(shí)算法。在只有訓(xùn)練樣本的前提下,找到幾何空間中所有樣本投影后離散度最小的投影方向,確定拒識(shí)區(qū)間,當(dāng)非訓(xùn)練樣本的測(cè)試樣本在投影方向上投影后,落在拒識(shí)區(qū)間,實(shí)現(xiàn)拒識(shí)功能。實(shí)驗(yàn)結(jié)果表明,該拒識(shí)算法能實(shí)現(xiàn)較高的拒識(shí)率,證實(shí)了該算法的有效性本文最終實(shí)現(xiàn)了一套基于OpenCV開發(fā)完整且可實(shí)際使用的步態(tài)識(shí)別系統(tǒng),不僅實(shí)時(shí)性強(qiáng),而且用戶界面友好。
[Abstract]:With the rapid development of computer vision technology, the demand for security is increasing day by day. Biometric identification, as a commonly used identification technology in security situations, has received extensive attention and research. Face, fingerprint and other biological features not only require close contact camera, but also high cost of recognition technology. Gait recognition has the characteristics of non-contact and concealment, which overcomes the defect of traditional biometric recognition which requires high resolution image. Based on OpenCV open source function library and the application of gait recognition in access control system, a complete gait recognition system is developed by using C and C as development tools. Furthermore, the rejection algorithm in gait recognition is deeply studied. In this paper, a complete gait recognition scheme is designed. With Matlab as the development tool, the samples in the large gait database CASIA-B provided by the Chinese Academy of Sciences automation are tested. The experimental results show that, The gait recognition scheme achieves an ideal recognition rate. On this basis, the following three aspects of the work completed: first, the use of C and C to achieve the entire gait recognition technology to form independent use of each functional module; second, build a complete gait image acquisition environment. The image acquisition environment is composed of camera module, monochromatic background and light to form a set of fixed acquisition environment to reduce the noise generated by external factors. Thirdly, a background detection and removal algorithm and rejection algorithm are proposed. After adding camera module, because of the actual environment noise interference, in the image preprocessing stage will produce a large number of noise (shadow, is not conducive to feature extraction, the image will be converted to YCrCb color space, The error between the target image and the background image is obtained, and the shadow position is found through the frame difference threshold and the shadow removal is realized. In addition, the access control system not only needs to satisfy the higher recognition rate in the practical application, but also has the function of refusing recognition, that is, it can not only accurately identify the real samples in the training sample database, but also refuse to recognize the false samples that do not belong to the training sample class. Therefore, in this paper, the recognition module in gait recognition is studied, and a rejection algorithm based on extremum optimization is proposed. On the premise of only training samples, the projection direction of the minimum dispersion of all samples after projection in geometric space is found, and the rejection interval is determined. When the untrained test sample is projected on the projection direction, it falls into the rejection interval. The function of refusing recognition is realized. Experimental results show that the rejection algorithm can achieve a high rejection rate. The validity of the algorithm is verified. Finally, a complete gait recognition system based on OpenCV is developed and can be used in practice. And the user interface is friendly.
【學(xué)位授予單位】：哈爾濱商業(yè)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

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙志杰;孫小英;金雪松;孫華東;盧鑫;;多重圖像輪廓特征結(jié)合的步態(tài)識(shí)別算法[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2016年04期

2 廖重陽(yáng);張洋;屈光中;畢云云;;基于Fisher判別字典學(xué)習(xí)的可拒識(shí)模式分類模型[J];計(jì)算機(jī)工程;2016年04期

3 康利攀;陳方福;范自柱;;一種新的拓展稀疏人臉識(shí)別算法[J];計(jì)算機(jī)應(yīng)用研究;2016年03期

4 王洪昌;丁立軍;黃宇;;生物信息學(xué)中模式識(shí)別技術(shù)應(yīng)用與發(fā)展[J];醫(yī)學(xué)信息學(xué)雜志;2013年11期

5 周洲;周林英;張鴿;;一種基于邊緣和形狀特征的教師目標(biāo)識(shí)別算法[J];西安工業(yè)大學(xué)學(xué)報(bào);2013年09期

6 鐘興志;王晨升;劉豐;郭世龍;;步態(tài)識(shí)別綜述[J];軟件;2013年04期

7 鄧亞麗;毋立芳;李云騰;;一種有效的圖像陰影自動(dòng)去除算法[J];信號(hào)處理;2011年11期

8 陳敬來;;基于中值背景模型的運(yùn)動(dòng)目標(biāo)自適應(yīng)檢測(cè)方法[J];科技廣場(chǎng);2011年05期

9 馮阿芳;石研;;軟件需求分析的思考[J];中國(guó)新技術(shù)新產(chǎn)品;2010年16期

10 黃志偉;張玉春;鄭創(chuàng)裕;;指紋身份論證技術(shù)提升建行系統(tǒng)競(jìng)爭(zhēng)力可行性分析[J];華南金融電腦;2009年09期

相關(guān)博士學(xué)位論文 前1條

1 胡榮;人體步態(tài)識(shí)別研究[D];華中科技大學(xué);2010年

相關(guān)碩士學(xué)位論文 前9條

1 吳晴;基于局部二值模式和非負(fù)矩陣分解的人臉表情識(shí)別[D];南京郵電大學(xué);2016年

2 商磊;基于動(dòng)作特征的視頻監(jiān)控網(wǎng)絡(luò)行人識(shí)別算法[D];浙江大學(xué);2016年

3 孫雪;圖像中環(huán)結(jié)構(gòu)特征及其應(yīng)用[D];中國(guó)海洋大學(xué);2015年

4 彭馨;基于視頻的手勢(shì)識(shí)別方法研究[D];東南大學(xué);2015年

5 魯友炳;基于生物特征的電子商務(wù)身份認(rèn)證平臺(tái)研究與設(shè)計(jì)[D];浙江工業(yè)大學(xué);2014年

6 齊建華;基于生物模式識(shí)別技術(shù)的WEB考勤管理系統(tǒng)研究[D];中國(guó)海洋大學(xué);2010年

7 曾瑩;基于角度及輪廓特征的步態(tài)識(shí)別方法研究[D];中南大學(xué);2008年

8 王曉冬;移動(dòng)陰影環(huán)境下的車輛視頻檢測(cè)算法研究[D];上海交通大學(xué);2007年

9 陳琦;論軟件項(xiàng)目開發(fā)的需求治理[D];北京郵電大學(xué);2006年

，

本文編號(hào)：1877218