本文選題：聯(lián)動標(biāo)定 + ViBe��； 參考：《華東交通大學(xué)》2017年碩士論文

【摘要】：現(xiàn)如今,視頻監(jiān)控技術(shù)廣泛應(yīng)用于銀行、超市、車站以及學(xué)校等公共區(qū)域的行人監(jiān)測。但是現(xiàn)有視頻監(jiān)控系統(tǒng)僅處于對視頻的記錄階段,無法精準(zhǔn)捕捉運動行人及其清晰外貌,這給公安刑偵人員調(diào)查取證帶來一定困難。因此,研究視頻監(jiān)控中的行人檢測與清晰外貌捕捉方法具有重大意義。頭肩檢測作為行人外貌捕捉的關(guān)鍵步驟,其目的在于準(zhǔn)確地獲取行人頭肩位置,為行人清晰外貌的捕捉提供可靠的前提條件。本文應(yīng)用圖像處理與機器學(xué)習(xí)技術(shù),開展了公共區(qū)域下行人頭肩檢測方法研究,主要研究內(nèi)容分為三個模塊,分別是運動目標(biāo)檢測模塊、行人頭肩檢測模塊以及主從攝像機聯(lián)動標(biāo)定模塊,具體工作及創(chuàng)新點如下:(1)針對行人清晰外貌捕捉要求,采用魚眼攝像機結(jié)合PTZ攝像機設(shè)計主從式監(jiān)控系統(tǒng),同時針對主從攝像機之間的聯(lián)動要求,應(yīng)用數(shù)據(jù)擬合的空間標(biāo)定算法,在合理選取樣本點的基礎(chǔ)上,依據(jù)樣本點在魚眼攝像機中的像素位置和PTZ攝像機拍攝樣本點所需旋轉(zhuǎn)的角度生成查找表,完成主從攝像機之間的聯(lián)動標(biāo)定,實現(xiàn)了主從攝像機之間的聯(lián)動要求。在整體行人頭肩檢測與清晰外貌捕捉系統(tǒng)搭建完成后的驗證表明,每5ms就可以完成一次主從攝像機之間的聯(lián)動。(2)針對傳統(tǒng)ViBe算法中存在的“死區(qū)”以及運動目標(biāo)陰影干擾問題,提出了結(jié)合感知哈希算法和基于圖像RGB色彩信息的高斯拉普拉斯差分算法的改進(jìn)ViBe算法,實現(xiàn)了對“死區(qū)”的抑制,消除了運動目標(biāo)陰影,完成了對視場范圍內(nèi)運動目標(biāo)的檢測。實驗表明,相較于傳統(tǒng)ViBe算法在視頻的1315幀才能完成對“死區(qū)”的抑制,改進(jìn)后的ViBe算法僅在視頻的15幀就完成了對“死區(qū)”的抑制,同時沒有了運動陰影的干擾。(3)針對行人頭肩檢測過程中誤檢率高的問題,提出兩階段頭肩檢測算法:首先,使用基于AdaBoost思想的級聯(lián)分類算法訓(xùn)練HOG特征生成第一階段頭肩檢測器,檢測出行人頭肩部位的“候選區(qū)域”;接著,使用SVM分類算法訓(xùn)練ORB特征生成第二階段頭肩檢測器,對“候選區(qū)域”進(jìn)行第二次檢測,并以此為最終結(jié)果。實驗表明,兩階段檢測算法頭肩檢測準(zhǔn)確率達(dá)到了80.86%,相較于傳統(tǒng)HOG+AdaBoost檢測算法準(zhǔn)確率提升了近10個百分點。
[Abstract]:Today, video surveillance technology is widely used in banks, supermarkets, stations, schools and other public areas of pedestrian monitoring. However, the existing video surveillance system is only in the recording stage of the video, which can not accurately capture the movement of pedestrians and their clear appearance, which makes it difficult for police investigators to investigate and obtain evidence. Therefore, it is of great significance to study pedestrian detection and clear appearance capture in video surveillance. Head-shoulder detection is a key step in pedestrian appearance capture, which aims at accurately obtaining the position of head and shoulder of pedestrians, and provides a reliable precondition for the capture of clear appearance of pedestrians. In this paper, using image processing and machine learning technology, the research of human head and shoulder detection method in public area downlink is carried out. The main research content is divided into three modules, which are moving target detection module. Pedestrian head-shoulder detection module and master-slave camera linkage calibration module. The specific work and innovation are as follows: 1) aiming at the requirements of pedestrian clear appearance capture, a master-slave monitoring system is designed with a fish-eye camera combined with a PTZ camera. At the same time, according to the requirements of the linkage between the master and slave cameras, the spatial calibration algorithm of data fitting is applied to select the sample points reasonably. According to the pixel position of the sample point in the fish-eye camera and the angle of rotation needed by the PTZ camera to shoot the sample point, the look-up table is generated, and the linkage calibration between the master-slave camera and the master-slave camera is completed, and the linkage requirement between the master-slave camera is realized. The verification of the whole pedestrian head-shoulder detection system and the clear appearance capture system shows that every 5ms can complete the linkage between the master and slave cameras once. (2) aiming at the problem of "dead zone" and shadow interference of moving targets in the traditional ViBe algorithm, An improved ViBe algorithm based on perceptual hashing algorithm and Gao Si Laplace difference algorithm based on image RGB color information is proposed, which can suppress the dead zone and eliminate the shadow of moving target. The detection of moving targets in the field of view is completed. The experimental results show that compared with the traditional ViBe algorithm, the "dead zone" can be suppressed only in 15 frames of the video by the improved ViBe algorithm, which can suppress the "dead zone" only in the 1315 frames of the video, and the improved ViBe algorithm can suppress the "dead zone" only in 15 frames of the video. At the same time, there is no interference of moving shadow. 3) aiming at the problem of high false detection rate in pedestrian head-shoulder detection, a two-stage head-shoulder detection algorithm is proposed: first, The concatenated classification algorithm based on AdaBoost is used to train the HOG feature to generate the first stage head-shoulder detector to detect the "candidate area" in the head and shoulder position of the traveller, and then the SVM classification algorithm is used to train the ORB feature to generate the second stage head-shoulder detector. The candidate regions were tested for a second time, and the results were taken as the final results. The experimental results show that the accuracy of head and shoulder detection is 80.86%, which is 10 percentage points higher than that of traditional HOG AdaBoost detection algorithm.
【學(xué)位授予單位】：華東交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄭慶慶;吳謹(jǐn);魏龍生;劉勁;;融合顏色和深度信息的圖像物體分割算法[J];模式識別與人工智能;2016年05期

2 孫國棟;林松;艾成漢;趙大興;;基于灰度直方圖反向投影的織物疵點圖像分割[J];制造業(yè)自動化;2016年04期

3 常旭劍;韓燮;熊風(fēng)光;;基于FAST檢測及SIFT描述的特征檢測算法[J];計算機工程與設(shè)計;2015年10期

4 王民;周兆鎮(zhèn);李昌華;衛(wèi)銘斐;毛力;;基于像素點灰度差的Harris角點檢測算法[J];計算機工程;2015年06期

5 古麗恰西·哈列勒別克;艾斯卡爾·艾木都拉;地里木拉提·吐爾遜;;基于基線鄰域Harris角點膨脹的維吾爾圖像文字區(qū)域檢測[J];激光雜志;2015年03期

6 丁PrPr;王鋒;;基于DM8148的警戒區(qū)域告警算法的實現(xiàn)[J];電子設(shè)計工程;2015年06期

7 黃蕾;鄒海;;基于相位一致的多尺度金字塔圖像特征提取[J];計算機技術(shù)與發(fā)展;2015年03期

8 李杰;徐汀榮;李海彥;;基于改進(jìn)LDP的人臉識別[J];計算機應(yīng)用與軟件;2014年05期

9 陳俊周;李煒;王春瑤;;一種動態(tài)場景下的視頻前景目標(biāo)分割方法[J];電子科技大學(xué)學(xué)報;2014年02期

10 梁慧妍;;判斷相似度快速分析油井示功圖[J];中國石油和化工標(biāo)準(zhǔn)與質(zhì)量;2013年05期

相關(guān)博士學(xué)位論文 前1條

1 萬定銳;雙目PTZ視覺系統(tǒng)的研究[D];清華大學(xué);2009年

相關(guān)碩士學(xué)位論文 前9條

1 劉俊麗;數(shù)字圖像處理演示系統(tǒng)[D];山東大學(xué);2015年

2 羅運俊;真實環(huán)境中人頭檢測系統(tǒng)的實現(xiàn)[D];山東大學(xué);2015年

3 馬蓓蓓;基于HOG特征的車輛檢測技術(shù)研究[D];華南理工大學(xué);2015年

4 桂斌;基于ViBe的運動目標(biāo)檢測與陰影消除方法研究[D];安徽大學(xué);2015年

5 陳翠霞;基于多特征級聯(lián)分類器的車輛檢測技術(shù)研究與實現(xiàn)[D];吉林大學(xué);2014年

6 石皓;用于全景與PTZ主從攝像機的標(biāo)定方法研究[D];國防科學(xué)技術(shù)大學(xué);2013年

7 謝成明;基于ORB特征的目標(biāo)檢測與跟蹤的研究[D];合肥工業(yè)大學(xué);2013年

8 石剛;增強現(xiàn)實中跟蹤注冊算法研究[D];蘇州大學(xué);2011年

9 張s，

本文編號：1799399