本文選題：視頻監(jiān)控系統(tǒng) + 運(yùn)動(dòng)目標(biāo)檢測(cè)�。� 參考：《南京信息工程大學(xué)》2017年碩士論文

【摘要】：隨著通信技術(shù)與計(jì)算機(jī)技術(shù)的發(fā)展,視頻監(jiān)控在日常安防中具有越來越重要的作用。傳統(tǒng)的視頻監(jiān)控模式主要是將采集視頻數(shù)據(jù)存儲(chǔ)到監(jiān)控中心的服務(wù)器中,僅有單一查看功能,已不能滿足用戶的需求。這種依靠人工對(duì)運(yùn)動(dòng)行人分析,不僅缺乏對(duì)異常信息及時(shí)預(yù)警的功能,而且準(zhǔn)確率較低。本文基于運(yùn)動(dòng)目標(biāo)檢測(cè)、行人識(shí)別與行人異常行為檢測(cè)算法展開研究,并設(shè)計(jì)智能視頻監(jiān)控系統(tǒng),該系統(tǒng)能夠?qū)\(yùn)動(dòng)行人異常行為發(fā)出警報(bào)。首先,為了更好的進(jìn)行運(yùn)動(dòng)目標(biāo)檢測(cè),提出了一種改進(jìn)的運(yùn)動(dòng)目標(biāo)檢測(cè)算法。結(jié)合圖像分塊和均值法建立背景模型,運(yùn)用圖像分塊與當(dāng)前幀自適應(yīng)權(quán)重更新背景模型,并采用自適應(yīng)閾值分割目標(biāo),克服了背景中運(yùn)動(dòng)殘影、光線變化干擾以及前景分割效果差的缺點(diǎn)。實(shí)驗(yàn)結(jié)果表明,本文方法能夠快速準(zhǔn)確檢測(cè)出運(yùn)動(dòng)目標(biāo)。其次,針對(duì)單特征行人識(shí)別度低的問題,提出了基于多特征融合的行人檢測(cè)算法。該方法融合了改進(jìn)的多尺度HOG特征與CSSF特征,全面準(zhǔn)確的描述了行人局部特征與全局特征。設(shè)計(jì)了一種Adaboost強(qiáng)分類器進(jìn)行行人檢測(cè)。在INRIA行人庫上的實(shí)驗(yàn)表明,本文方法大幅提高了行人檢測(cè)精度。然后,針對(duì)行人異常行為檢測(cè)中存在的問題,在目標(biāo)跟蹤基礎(chǔ)上,對(duì)行人的形狀和運(yùn)動(dòng)軌跡特征進(jìn)行多特征提取,充分描述了行人行為信息,并運(yùn)用先驗(yàn)知識(shí)對(duì)上述特征進(jìn)行量化,檢測(cè)行人異常行為。實(shí)驗(yàn)結(jié)果表明,本文方法能夠有效檢測(cè)行人異常行為,包括異常摔倒、異常跑步和徘徊。最后,在上述算法基礎(chǔ)上,對(duì)智能視頻監(jiān)控系統(tǒng)需求進(jìn)行分析與設(shè)計(jì),利用VisualStudio、OpenCV、Android、javaweb、云服務(wù)器等技術(shù)進(jìn)行開發(fā),從而使系統(tǒng)智能化、移動(dòng)化。實(shí)驗(yàn)表明系統(tǒng)運(yùn)行流程,實(shí)時(shí)性與準(zhǔn)確性較好,能夠滿足用戶遠(yuǎn)程監(jiān)控、并及時(shí)準(zhǔn)確掌握行人異常行為信息的功能需求。
[Abstract]:With the development of communication technology and computer technology, video surveillance plays a more and more important role in daily security. The traditional video surveillance mode is mainly to store the collected video data in the server of the monitoring center, which can not meet the needs of the users only with a single viewing function. This kind of artificial pedestrian analysis not only lacks the function of timely warning of abnormal information, but also has low accuracy. Based on moving target detection, pedestrian recognition and pedestrian abnormal behavior detection algorithms, an intelligent video surveillance system is designed, which can alert the abnormal behavior of moving pedestrians. Firstly, in order to detect moving targets better, an improved moving target detection algorithm is proposed. The background model is established by combining the method of image segmentation and mean, and the background model is updated by image segmentation and current frame adaptive weight, and the target is segmented by adaptive threshold, which overcomes the moving image in the background. The disturbance of light change and the disadvantage of poor foreground segmentation. The experimental results show that the proposed method can detect moving targets quickly and accurately. Secondly, a pedestrian detection algorithm based on multi-feature fusion is proposed to solve the problem of low recognition degree of single feature pedestrian. This method combines the improved multi-scale HOG features with the CSSF features, and describes the local and global features of pedestrians comprehensively and accurately. A Adaboost strong classifier is designed for pedestrian detection. The experimental results on the INRIA pedestrian depot show that the proposed method greatly improves the pedestrian detection accuracy. Then, aiming at the problems in pedestrian abnormal behavior detection, based on the target tracking, the multi-feature extraction of pedestrian shape and trajectory features is carried out, which fully describes the pedestrian behavior information. A priori knowledge is used to quantify the above characteristics to detect the abnormal behavior of pedestrians. The experimental results show that the proposed method can effectively detect abnormal pedestrian behavior, including abnormal fall, abnormal running and wandering. Finally, on the basis of the above algorithms, the requirements of intelligent video surveillance system are analyzed and designed, and developed by using Visual Studio OpenCVN Android Java web, cloud server and so on, so as to make the system intelligent and mobile. The experimental results show that the system has good real-time and accuracy and can meet the functional requirements of remote monitoring and timely and accurate understanding of pedestrian abnormal behavior information.
【學(xué)位授予單位】：南京信息工程大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN948.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王恬;李慶武;劉艷;周亞琴;;利用姿勢(shì)估計(jì)實(shí)現(xiàn)人體異常行為識(shí)別[J];儀器儀表學(xué)報(bào);2016年10期

2 張?zhí)?張為;劉艷艷;;周界視頻監(jiān)控中人員翻越行為檢測(cè)算法[J];西安交通大學(xué)學(xué)報(bào);2016年06期

3 田仙仙;鮑泓;徐成;;一種改進(jìn)HOG特征的行人檢測(cè)算法[J];計(jì)算機(jī)科學(xué);2014年09期

4 黃凱奇;陳曉棠;康運(yùn)鋒;譚鐵牛;;智能視頻監(jiān)控技術(shù)綜述[J];計(jì)算機(jī)學(xué)報(bào);2015年06期

5 韓明;劉教民;孟軍英;王震洲;;一種自適應(yīng)調(diào)整K-r的混合高斯背景建模和目標(biāo)檢測(cè)算法[J];電子與信息學(xué)報(bào);2014年08期

6 顧會(huì)建;陳俊周;;基于改進(jìn)顏色自相似特征的行人檢測(cè)方法[J];計(jì)算機(jī)應(yīng)用;2014年07期

7 邱聯(lián)奎;劉啟亮;雷文龍;;基于背景減除與三幀差分相融合的運(yùn)動(dòng)檢測(cè)[J];合肥工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年05期

8 屈晶晶;辛云宏;;連續(xù)幀間差分與背景差分相融合的運(yùn)動(dòng)目標(biāo)檢測(cè)方法[J];光子學(xué)報(bào);2014年07期

9 茍娟迎;;基于背景差分法的運(yùn)動(dòng)目標(biāo)分割[J];工業(yè)控制計(jì)算機(jī);2013年08期

10 高美鳳;劉娣;;分塊幀差和背景差相融合的運(yùn)動(dòng)目標(biāo)檢測(cè)[J];計(jì)算機(jī)應(yīng)用研究;2013年01期

相關(guān)碩士學(xué)位論文 前3條

1 李江;基于Android的4G網(wǎng)絡(luò)移動(dòng)高清視頻監(jiān)控系統(tǒng)關(guān)鍵技術(shù)的研究[D];浙江大學(xué);2016年

2 魚亞鋒;運(yùn)動(dòng)目標(biāo)檢測(cè)和智能視頻監(jiān)控系統(tǒng)設(shè)計(jì)[D];北京郵電大學(xué);2008年

3 趙強(qiáng);基于FTP協(xié)議的文件傳輸服務(wù)器的研究[D];大連海事大學(xué);2008年

，

本文編號(hào)：1969989