發(fā)布時(shí)間：2018-02-21 23:51

  本文關(guān)鍵詞： 智能視頻監(jiān)控 人臉識(shí)別 步態(tài)識(shí)別 體態(tài)識(shí)別 骨骼跟蹤　出處：《電子科技大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：智能視頻監(jiān)控系統(tǒng)近幾年在計(jì)算機(jī)視覺領(lǐng)域發(fā)展迅速,并成為該領(lǐng)域的重要研究方向。生物特征識(shí)別技術(shù)是指利用人體的固有特征進(jìn)行身份鑒別的計(jì)算機(jī)技術(shù),廣泛應(yīng)用于銀行、司法等身份鑒別領(lǐng)域。將人體生物特征識(shí)別技術(shù)應(yīng)用到智能視頻監(jiān)控系統(tǒng)中,構(gòu)建自動(dòng)身份識(shí)別及處理系統(tǒng)。應(yīng)用于智能視頻監(jiān)控中的生物特征識(shí)別受光照、環(huán)境噪聲以及人體運(yùn)動(dòng)等因素的干擾,實(shí)現(xiàn)起來較基于靜態(tài)圖片的生物特征識(shí)別困難。因此,分析、研究智能視頻監(jiān)控系統(tǒng)中對(duì)生物特征識(shí)別造成干擾的因素具有很大的應(yīng)用價(jià)值。研究智能視頻監(jiān)控系統(tǒng)中的生物特征識(shí)別方法是本文的研究重點(diǎn)。本文研究目的是通過對(duì)智能視頻監(jiān)控系統(tǒng)中生物特征識(shí)別算法進(jìn)行研究,提升系統(tǒng)中人體身份識(shí)別的準(zhǔn)確率,為智能視頻監(jiān)控系統(tǒng)的真正應(yīng)用做出貢獻(xiàn)。在監(jiān)控視頻中,生物特征識(shí)別具有非接觸性和非侵犯性的特點(diǎn)。其中,能夠用于身份鑒別的特征有人臉特征、步態(tài)特征以及體形體態(tài)特征。本文分別對(duì)這三種特征進(jìn)行分析研究,并提出相應(yīng)的特征識(shí)別算法。本文的主要工作有:1、研究人臉識(shí)別技術(shù),首先對(duì)智能視頻監(jiān)控中獲取的人臉圖像處理方法進(jìn)行分析,通過預(yù)處理得到利于識(shí)別的人臉圖像。然后通過對(duì)傳統(tǒng)的LBP算法進(jìn)行研究和改進(jìn),提出了改進(jìn)后的LBP人臉識(shí)別算法。該方法通過計(jì)算區(qū)域內(nèi)的均值和方差,求得該鄰域的四值模式。通過實(shí)驗(yàn)驗(yàn)證,該算法的識(shí)別率較傳統(tǒng)LBP算法有所提高、魯棒特性好。最后將改進(jìn)的LBP算子應(yīng)用于人臉識(shí)別系統(tǒng)。2、研究步態(tài)特征提取方法,提出基于Kinect的步態(tài)特征提取方法。運(yùn)用Kinect能夠提取三種步態(tài)特征,分別是:雙腿關(guān)節(jié)點(diǎn)角度信息、行走時(shí)的步幅特征以及三維人體輪廓描述子。介紹了Kinect的深度獲取以及骨骼獲取原理,并通過Kinect的坐標(biāo)空間轉(zhuǎn)換得到三維人體輪廓。最后采用最近鄰分類器和k-近鄰分類器進(jìn)行實(shí)驗(yàn),實(shí)驗(yàn)表明文中提出的基于Kinect的步態(tài)識(shí)別方法有效,識(shí)別率達(dá)到84%。3、嘗試性的提出體態(tài)識(shí)別方法,分析體態(tài)特征用于身份鑒別的理論依據(jù)以及限制條件。定義人體體態(tài)特征,然后使用Kinect的骨骼跟蹤功能對(duì)人體體態(tài)特征進(jìn)行提取。最后分別使用標(biāo)準(zhǔn)歐式距離分類器、方差倒數(shù)加權(quán)歐式距離分類器以及決策樹分類方法進(jìn)行實(shí)驗(yàn),表明該人體體態(tài)識(shí)別方法有效,最高識(shí)別率達(dá)到87%。
[Abstract]:Intelligent video surveillance system has developed rapidly in the field of computer vision in recent years, and has become an important research direction in this field. It is widely used in bank, judicial and other identification fields. The technology of human biometric identification is applied to the intelligent video surveillance system, and the automatic identification and processing system is constructed. The biometric identification used in intelligent video surveillance is illuminated. It is more difficult to realize biometric recognition based on static picture because of the interference of environmental noise and human body movement. It is of great value to study the factors that interfere with biometric identification in intelligent video surveillance system. The research of biometric recognition method in intelligent video surveillance system is the focus of this paper. It is based on the research of biometric recognition algorithm in intelligent video surveillance system. Enhance the accuracy of human identification in the system, and contribute to the real application of intelligent video surveillance system. In surveillance video, biometric recognition has the characteristics of non-contact and non-invasive. The features that can be used for identification are facial features, gait features and body features. The main work of this paper is to study the face recognition technology. Firstly, the face image processing method obtained from intelligent video surveillance is analyzed. Through the research and improvement of the traditional LBP algorithm, an improved LBP face recognition algorithm is proposed, which calculates the mean value and variance in the region. The quad-valued pattern of the neighborhood is obtained. The experimental results show that the recognition rate of the algorithm is better than that of the traditional LBP algorithm. Finally, the improved LBP operator is applied to face recognition system .2and the gait feature extraction method is studied. A gait feature extraction method based on Kinect is proposed. Three gait features can be extracted by using Kinect. The characteristics of walking stride and 3D human outline descriptor. The principle of depth acquisition and bone acquisition of Kinect is introduced. Finally, the nearest neighbor classifier and k- nearest neighbor classifier are used to experiment. The experiment shows that the proposed gait recognition method based on Kinect is effective. The recognition rate is 84%. 3. Try to put forward a method of body recognition, analyze the theoretical basis and limiting conditions of body feature used for identity identification, and define the body characteristics of human body. Then we use the skeleton tracking function of Kinect to extract the human body features. Finally, we use standard Euclidean distance classifier, variance-reciprocal weighted Euclidean distance classifier and decision tree classification method to carry out experiments. The results show that the method is effective and the highest recognition rate is 87.
【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】：2014
【分類號(hào)】：TP391.41;TN948.6
，

本文編號(hào)：1523159