一种基于动态图像的多目标识别计数方法
|
摘要
动态图像多目标识别与计数，在医学研究、交通监视、客流量统计、天文观测等领域有着非常重要的实用价值和广阔的发展前景。利用图像处理和模式识别技术对运动多目标进行跟踪计数是一种先进的计数手段，是目前国内研究的一个热点。
动态图像多目标识别与跟踪计数是图像处理的一个重要方面。它包括了运动目标的检测、目标分类与提取、目标跟踪与计数几方面，涉及到图像处理与模式识别领域许多核心课题。本论文以“商场客流量图像统计系统”项目为背景，研究了一类运动多目标跟踪计数问题。在本算法中，为了尽可能避免目标的重叠或覆盖的现象，将CCD摄像机安装在获取图像的正上方。并在实验室模拟了一类简单的进出商场人运动情况的动态目标识别与跟踪计数系统。
在本算法完成系统初始化后，首先，利用本文提出的一种改进的自适应运动目标检测方法，检测运动目标是否存在。该方法能有效抑制光照变化、人影、噪声等影响；其次，采用较有效的图像滤波、图像分割、形态学处理等方法对图像进行处理。并根据统计特征清除了伪目标，提取出人头部真正目标，选择了能反映目标不变特征；最后，在比较几种常用多目标跟踪算法的基础上，本算法采用特征跟踪方法对该类多目标进行跟踪计数。跟踪计数是本算法的一个难点。根据该类多目标在相邻帧间运动具有连续性，并且包围窗口变化不大的特点，本跟踪计数算法改进了一种代价函数，应用于图像跟踪的匹配过程中。启动了卡尔曼滤波，预测目标匹配搜索区域。同时，使用目标链记录了目标最新的运动状态和特征值，保证了运动跟踪的连续性。在跟踪过程中考虑了目标暂时静止、消失、交叉多种情况，并对动态图像中帧间出现新目标进行了正确处理，实现了多目标的正确的跟踪，进而对运动目标是否在跟踪区域徘徊进行判断，保证了进出目标计数的正确性。
通过大量实验，本算法对该类动态图像多目标的跟踪计数取得较好效果，计数结果基本上与实际相符。
Multi-object recognition and counting in dynamic image has the very important applied value and prospective scene in such fields as the research of the medicine, the transportation monitor statistics of passenger volume and observation of the astronomy. It's a kind of advanced counting ways to adopt the technology of the image processing and pattern recognition to track and count the moving multi-target. At present, the technology has been become one of research hotspots.
Multi-object recognition and counting in dynamic image is an important aspect of the image processing which includes detection classification feature extraction tracking and counting of the moving objects. And many kernel subjects are involved in the fields of image processing and pattern identification.
This paper is based on the project "the statistic system of the passenger volume in the shop." A tracking and counting problem is researched on a kind of moving multi-object. The CCD camera is placed above the preyed image so that the overlap phenomenon of the objects can be avoided in the algorithm.
Firstly, an advanced approach on moving objects is put forward in this paper, and it is used to detect whether moving objects exist. To a certain degree, this approach can restrain the affection such as the variant shinning shadow noise and so on.
Secondly, an effective approach is adopted such as the image filtering, image segmentation, morphology processing and so on. According to the statistic features, false objects are cleared and the true objects of the heads are extracted to choose the invariable features of the objects.
Finally, on the base of the normal algorithms about multi-object tracking, the feature-based tracking approach is adopted to track and count the kind of multi-object in the algorithm, in which the tracking and counting is one of the difficulties. Regarding of the moving continuity and the small change of object's features in frames, a kind of cost function is put forward in the tracking and counting algorithm, which is applied in the tracking match of the image. At the same time, the Kalman filter is used to predicate the search areas of the matching objects, and then,
moving state and feature value of the objects in current frame are recorded to ensure the continuity of the dynamic tracking depended on the object-chain. This method can reduce the searching areas of the objects. In the process of tracking, when the objects rest disappear cross, or the new objects appear between the frames in the dynamic image, the algorithm can solve it correctly to realize the proper tracking of the multi-object, what's more, it correctly judges whether dynamic objects wander in the tracking areas, which ensures the validity of the counting.
Based on a large number of experiments, the algorithm has a good effect on tracking and counting of a kind multi-object in dynamic images and counting results coincides with the fact basically.
动态图像多目标识别与跟踪计数是图像处理的一个重要方面。它包括了运动目标的检测、目标分类与提取、目标跟踪与计数几方面，涉及到图像处理与模式识别领域许多核心课题。本论文以“商场客流量图像统计系统”项目为背景，研究了一类运动多目标跟踪计数问题。在本算法中，为了尽可能避免目标的重叠或覆盖的现象，将CCD摄像机安装在获取图像的正上方。并在实验室模拟了一类简单的进出商场人运动情况的动态目标识别与跟踪计数系统。
在本算法完成系统初始化后，首先，利用本文提出的一种改进的自适应运动目标检测方法，检测运动目标是否存在。该方法能有效抑制光照变化、人影、噪声等影响；其次，采用较有效的图像滤波、图像分割、形态学处理等方法对图像进行处理。并根据统计特征清除了伪目标，提取出人头部真正目标，选择了能反映目标不变特征；最后，在比较几种常用多目标跟踪算法的基础上，本算法采用特征跟踪方法对该类多目标进行跟踪计数。跟踪计数是本算法的一个难点。根据该类多目标在相邻帧间运动具有连续性，并且包围窗口变化不大的特点，本跟踪计数算法改进了一种代价函数，应用于图像跟踪的匹配过程中。启动了卡尔曼滤波，预测目标匹配搜索区域。同时，使用目标链记录了目标最新的运动状态和特征值，保证了运动跟踪的连续性。在跟踪过程中考虑了目标暂时静止、消失、交叉多种情况，并对动态图像中帧间出现新目标进行了正确处理，实现了多目标的正确的跟踪，进而对运动目标是否在跟踪区域徘徊进行判断，保证了进出目标计数的正确性。
通过大量实验，本算法对该类动态图像多目标的跟踪计数取得较好效果，计数结果基本上与实际相符。
Multi-object recognition and counting in dynamic image has the very important applied value and prospective scene in such fields as the research of the medicine, the transportation monitor statistics of passenger volume and observation of the astronomy. It's a kind of advanced counting ways to adopt the technology of the image processing and pattern recognition to track and count the moving multi-target. At present, the technology has been become one of research hotspots.
Multi-object recognition and counting in dynamic image is an important aspect of the image processing which includes detection classification feature extraction tracking and counting of the moving objects. And many kernel subjects are involved in the fields of image processing and pattern identification.
This paper is based on the project "the statistic system of the passenger volume in the shop." A tracking and counting problem is researched on a kind of moving multi-object. The CCD camera is placed above the preyed image so that the overlap phenomenon of the objects can be avoided in the algorithm.
Firstly, an advanced approach on moving objects is put forward in this paper, and it is used to detect whether moving objects exist. To a certain degree, this approach can restrain the affection such as the variant shinning shadow noise and so on.
Secondly, an effective approach is adopted such as the image filtering, image segmentation, morphology processing and so on. According to the statistic features, false objects are cleared and the true objects of the heads are extracted to choose the invariable features of the objects.
Finally, on the base of the normal algorithms about multi-object tracking, the feature-based tracking approach is adopted to track and count the kind of multi-object in the algorithm, in which the tracking and counting is one of the difficulties. Regarding of the moving continuity and the small change of object's features in frames, a kind of cost function is put forward in the tracking and counting algorithm, which is applied in the tracking match of the image. At the same time, the Kalman filter is used to predicate the search areas of the matching objects, and then,
moving state and feature value of the objects in current frame are recorded to ensure the continuity of the dynamic tracking depended on the object-chain. This method can reduce the searching areas of the objects. In the process of tracking, when the objects rest disappear cross, or the new objects appear between the frames in the dynamic image, the algorithm can solve it correctly to realize the proper tracking of the multi-object, what's more, it correctly judges whether dynamic objects wander in the tracking areas, which ensures the validity of the counting.
Based on a large number of experiments, the algorithm has a good effect on tracking and counting of a kind multi-object in dynamic images and counting results coincides with the fact basically.
引文
[1]K．R．Castleman 数字图象处理．北京：电子工业出版社，1998．
[2]边肇祺，张学工．模式识别．北京：清华大学出版社，2000．
[3]李智勇，沈振康，杨卫平．动态图象分析 北京：国防工业出版社，1999
[4]谷口庆治．数字图像处理 北京：科学出版社，2002
[5]吴健康．图象处理与分析．北京：人民邮电出版社，1989．
[6]荆仁杰．计算机图象处理．杭州：浙江大学出版社，1990．
[7]R．C 冈萨雷斯，P．温茨．数字图象处理．北京：科学出版社，1983．
[8]王耀南 计算机图像处理与识别技术．北京：高等教育出版社，2001
[9]阮秋琦．数字图象处理学．北京：电子工业出版社，2001．
[10]章毓晋．图象处理和分析．北京：清华大学出版社，2000．
[11]郭桂蓉．模糊模式识别．长沙：国防科技大学出版社，1989．
[12]章毓晋．图象分割．北京：科学出版社，2001．
[13]孙即祥 等 模式识别中的特征提取与计算机视觉不变量．北京：国防工业出版社，2001
[14]图象识别导论．北邮模式识别与智能系统实验室网站．2001
[15]傅德胜，寿益禾．图形图像处理学．南京：东南大学出版社，2001
[16]傅京孙．模式识别应用．北京：北京大学出版社，1990．
[17]沈庭芝，方子文．数字图象处理及模式识别．北京：北京理工大学出版社，2000
[18]容观澳．计算机图象处理．北京：清华大学出版社，2000．
[19]徐飞，施晓红．MATLAB应用图像处理．西安：西安电子科技大学出版社，2002
[20]杨枝灵，王开．Visual C++数字图像获取处理及实践应用．北京：人民邮电出版社，2003
[21]苏开娜，任文君，易小琳 基于运动模型的道路识别与跟踪算法的研究．中国图象图形学报，2000，Vol．5(A)，No．3
[22]刘国衡，关玉才 图象序列的目标检测．计算机工程与应用，1997，8．
[23]Roy Wang, Hong-Jiang Zhang. A confidence measure based moving object extraction system built for compressed domain
[24]匡宇，游志胜．精子运动图象多目标检测与分割．第九届全国图象图形学学术会议论文集
[25]Tianxu ,Weixue Lu and Jiangxiong Peng. Adaptive Image Matching Via Spatial Varying Grey-Level Correction. IEEE Transactions on Communication, 1995, 43(5).
[26]K.Akita, Image Sequence Analysis of Real World Human Motion, Pattern Recognition, Vol.17, No.4, PP.73-83, 1984.
[27]Zhang Tianxu, Sang Nong,Wang Guoyou &Li Xiaowen. An effective method for identifying small objects on a complicated background. Aritificial Intelligence in Engineering , 1996, (10).
[28]庄涛，王人成．一种运动图像标志点识别跟踪方法的研究．系统工程与电子技术 2002，Vol．24，No．4
[29]王丰元、孙壮志．一种基于哈夫变换圆形物体检测技术．第九届全国图象图形学学术会议论文集
[30]何斌，马天予．Visual C++数字图像处理．北京：人民邮电出版社，2001
[31]王新红、钱建生．用图象处理的方法监测原煤块率的研究．第九届全国图象图形学学术会议论文集
[32]王秋让、赵荣椿．基于图象结构的门限自动选择及目标提取．第九届全国图象图形学学术会议论文集
[33]韩军伟、郭雷．景物边缘提取的独立边缘自增强算法．电子学报 2002，4
[34]郑军，马建峰，王信义．二值图象的目标识别技术．机械 2002，Vol(29)，No(2)
[35]董志荣、苗艳、李艳丽．目标定位和跟踪的卡尔曼滤波加BP神经网络的方法．火力与指挥控制 1988，3
[36]江静，孙晶华，贺利洁．目标识别中的遗传算法研究．佳木斯大学学报 2002，3 Vol．20 No．1
[37]钟伟，余松煜，芮雨．图象序列处理中的形态分割方法 上海交通大学学报 2001，9 P．1314
[38]李国宽、李红、彭嘉雄．从图象序列中检测定位小目标的一种方法．华中理工大学学报 1999，8 P．63
[39]韩军，熊璋，孙文彦．自动分割及跟踪视频运动对象的一种实现方法 中国图象图形学报，2001，6(A)：P732．
[40]Olivier.Rioul and Martin.Vetterll. Wavelets and Signal Processing.
IEEE SP MAGAZINE, 1991, (10).
[41]Illmination Independent change Detection for Real World Image Sequences. Computer Vision, Graphics, and Image Processing, 1989, 46
[42]Azriel Rosenfeld. Image analysis: problems, progress, and prospects. Pattern Recognition, 1984, 17(1).
[43]Jon Sticklen and Anil K.Jain. Knowledge-Based Segmentation of Landsat Images Jezching Ton. IEEE Transactions on Geoscience and Remote Sensing, 1991, 29(2).
[44]富煜清，沈巍，黄心晔．车牌照的提取方法研究．模式识别与人工智能 2000，13(3)：P345．
[45]王秋让，赵荣椿，郑南宁．一种航空照片中的小目标识别方法．中国图象图形学报，1998，3(12)：P993．
[46]王润生，文贡坚．面向百类目标的自动识别系统．中国图象图形报，1998，3(4)：P263．
[47]周锐，杨涤 复杂背景中目标图像中的提取与跟踪．系统工程与电子技术，1997
[48]周志明，汪亚明 基于运动区域的多目标检测．计算机测量与控制，2002，10(7)
[49]张嫣，姚耀文 运动图像序列中多目标跟踪的研究与实现．计算机应用研究 2002：P74．
[50]徐毓，李锋，金以慧 基于聚类融合的多目标跟踪算法．传感器技术，2002，21(7)：P31
[51]B.COIFMAN, D.BEYMER, EMCLAUCHLAN, A real-time computer vision system for vehicle tracking and traffic surveillance[J].Transportation Research Part C, 1998, 6: P271-288.
[52]J. FERRU, A. OLLERO. Integrated real-time vision system for vehicle control in nonstructured environments. Engineering Applications of Artificial Intelligence[J].2000, 13:P215-236
[53]FRANCOIS G.MEYER, PATRICK BOUTHEMY. Region-based tracking using a fine motion models in long image sequences[J].Computer Vision, Graphics, and lmageprocessing(CVGIP), 1994, 60(2): P119-140.
[54]JORGE BADENAS, F.PLA.Segmentation based on region-tracking in image sequences for traffic monitoring.In 14th international Conference on Pattern
Recognition, ICPR, 1998: P999-1001.-+
[55]D.Beymer and K.Konolige. Real-time tracking of multiple people using stereo.In IEEE Frame Rate Workshop, 1999.
[56]徐大为，顾樑，刘重庆 航拍图像中运动车辆的检测与定位．计算机工程 2002，Vol．28，No．9
[57]刘亚，艾海舟，徐光佑 一种基于背景模型的运动目标检测与跟踪算法．信息与控制 2002，Vol．31，No．4
[58]路迈西，王勇 利用阈值分割技术提取煤泥浮选泡沫图像的物理特征．煤炭科学技术 2002，Vol．30，No．8
[59]A.Bobick and J.Davis. Real-time recognition of activity using temporal templates. In IEEE Workshop on Application of Computer Vision, Pages 1233-1251,1996.
[60]D.Comaniciu, V.Ramesh, P.Meer. Real Time Tracking of Non-Rigid Objects using Mean Shift. In Computer Vision and Pattern Recognition conference, 2000.
[61]史立，张兆扬，马然 基于运动跟踪匹配技术的视频对象提取．通信学报，2001，Vol．22，No．11
[62]余洪山，王耀南 一种新型智能图像监控系统．信号与控制，2002，Vol．31，No．6
[63]白雪生，金国英 基于帧间运动的视频分割．清华大学学报，2002，Vol．42，No．1
[64]张玲华 对有背景的图像实现运动目标的边界检测．南京邮电学院学报，1997，Vol．17，No．3
[65]祝远新，徐光佑 一种基于块匹配的鲁棒运动估计算法．中国图象图形学报，1998，Vol．3，No．9
[66]王亮，胡卫明，谭铁牛 人运动的视觉分析综述．计算机学报，2002，Vol．25，No．3
[67]Cui.Y and Weng.J. Hand segmentation using learning-based prediction and verification for hand sign recognition. In:Proc IEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico. 1997.P88-93.
[68]Haritaoglu I. Harwood D and Davis L.W~4: real-time surveillance of people and their activities.IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
[69]Aggarwal J and Cai Q.Human motion analysis: a review. Computer Vision and
Image Understanding. 1999.73(3): 428-440.
[70]Yang J and Waibel A. A real-time face tracker. In:Proc IEEE Workshop on Applications of Computer Vision. Sarasota.USA. 1996.142-147.
[71]王岩松，阮秋琦 一种基于互相关的图像定位匹配算法研究与应用．北方交通大学学报，2002，Vol．26
[72]刘新海，方康玲 一种基于灰度特征的快速识别定位算法．三峡大学学报，2002，2．
[73]郑江滨，张艳宁，冯大淦 视频监视中运动目标的检测与跟踪算法．系统工程与电子技术，Vol．24，No．10
[74]艾海舟，王拴，何克忠．基于差分图象的人脸检测．中国图象图形学报，1998，3(12)：P987．
[75]杨绍清，贾传荧．基于模糊判决的图象边缘连接．光学技术，2002，3，Vol．28 No．2
[76]王拴，艾海舟，何克忠．基于差分图象的多运动目标的检测与跟踪．中国图象图形学报，1999，4(6)：P470．
[77]罗希平，田捷等．图象分割方法综述．模式识别与人工智能，1999，12(3)：P300
[78]CHEN Xing-zhi, WANG Qing-yang. Image Motion Detect And Digital Store System. Technology of TV. 1998, (7):23～26(ch).
[79]张有为 维纳与卡尔曼滤波理论导论 北京：人民教育出版社，1980．
[2]边肇祺，张学工．模式识别．北京：清华大学出版社，2000．
[3]李智勇，沈振康，杨卫平．动态图象分析 北京：国防工业出版社，1999
[4]谷口庆治．数字图像处理 北京：科学出版社，2002
[5]吴健康．图象处理与分析．北京：人民邮电出版社，1989．
[6]荆仁杰．计算机图象处理．杭州：浙江大学出版社，1990．
[7]R．C 冈萨雷斯，P．温茨．数字图象处理．北京：科学出版社，1983．
[8]王耀南 计算机图像处理与识别技术．北京：高等教育出版社，2001
[9]阮秋琦．数字图象处理学．北京：电子工业出版社，2001．
[10]章毓晋．图象处理和分析．北京：清华大学出版社，2000．
[11]郭桂蓉．模糊模式识别．长沙：国防科技大学出版社，1989．
[12]章毓晋．图象分割．北京：科学出版社，2001．
[13]孙即祥 等 模式识别中的特征提取与计算机视觉不变量．北京：国防工业出版社，2001
[14]图象识别导论．北邮模式识别与智能系统实验室网站．2001
[15]傅德胜，寿益禾．图形图像处理学．南京：东南大学出版社，2001
[16]傅京孙．模式识别应用．北京：北京大学出版社，1990．
[17]沈庭芝，方子文．数字图象处理及模式识别．北京：北京理工大学出版社，2000
[18]容观澳．计算机图象处理．北京：清华大学出版社，2000．
[19]徐飞，施晓红．MATLAB应用图像处理．西安：西安电子科技大学出版社，2002
[20]杨枝灵，王开．Visual C++数字图像获取处理及实践应用．北京：人民邮电出版社，2003
[21]苏开娜，任文君，易小琳 基于运动模型的道路识别与跟踪算法的研究．中国图象图形学报，2000，Vol．5(A)，No．3
[22]刘国衡，关玉才 图象序列的目标检测．计算机工程与应用，1997，8．
[23]Roy Wang, Hong-Jiang Zhang. A confidence measure based moving object extraction system built for compressed domain
[24]匡宇，游志胜．精子运动图象多目标检测与分割．第九届全国图象图形学学术会议论文集
[25]Tianxu ,Weixue Lu and Jiangxiong Peng. Adaptive Image Matching Via Spatial Varying Grey-Level Correction. IEEE Transactions on Communication, 1995, 43(5).
[26]K.Akita, Image Sequence Analysis of Real World Human Motion, Pattern Recognition, Vol.17, No.4, PP.73-83, 1984.
[27]Zhang Tianxu, Sang Nong,Wang Guoyou &Li Xiaowen. An effective method for identifying small objects on a complicated background. Aritificial Intelligence in Engineering , 1996, (10).
[28]庄涛，王人成．一种运动图像标志点识别跟踪方法的研究．系统工程与电子技术 2002，Vol．24，No．4
[29]王丰元、孙壮志．一种基于哈夫变换圆形物体检测技术．第九届全国图象图形学学术会议论文集
[30]何斌，马天予．Visual C++数字图像处理．北京：人民邮电出版社，2001
[31]王新红、钱建生．用图象处理的方法监测原煤块率的研究．第九届全国图象图形学学术会议论文集
[32]王秋让、赵荣椿．基于图象结构的门限自动选择及目标提取．第九届全国图象图形学学术会议论文集
[33]韩军伟、郭雷．景物边缘提取的独立边缘自增强算法．电子学报 2002，4
[34]郑军，马建峰，王信义．二值图象的目标识别技术．机械 2002，Vol(29)，No(2)
[35]董志荣、苗艳、李艳丽．目标定位和跟踪的卡尔曼滤波加BP神经网络的方法．火力与指挥控制 1988，3
[36]江静，孙晶华，贺利洁．目标识别中的遗传算法研究．佳木斯大学学报 2002，3 Vol．20 No．1
[37]钟伟，余松煜，芮雨．图象序列处理中的形态分割方法 上海交通大学学报 2001，9 P．1314
[38]李国宽、李红、彭嘉雄．从图象序列中检测定位小目标的一种方法．华中理工大学学报 1999，8 P．63
[39]韩军，熊璋，孙文彦．自动分割及跟踪视频运动对象的一种实现方法 中国图象图形学报，2001，6(A)：P732．
[40]Olivier.Rioul and Martin.Vetterll. Wavelets and Signal Processing.
IEEE SP MAGAZINE, 1991, (10).
[41]Illmination Independent change Detection for Real World Image Sequences. Computer Vision, Graphics, and Image Processing, 1989, 46
[42]Azriel Rosenfeld. Image analysis: problems, progress, and prospects. Pattern Recognition, 1984, 17(1).
[43]Jon Sticklen and Anil K.Jain. Knowledge-Based Segmentation of Landsat Images Jezching Ton. IEEE Transactions on Geoscience and Remote Sensing, 1991, 29(2).
[44]富煜清，沈巍，黄心晔．车牌照的提取方法研究．模式识别与人工智能 2000，13(3)：P345．
[45]王秋让，赵荣椿，郑南宁．一种航空照片中的小目标识别方法．中国图象图形学报，1998，3(12)：P993．
[46]王润生，文贡坚．面向百类目标的自动识别系统．中国图象图形报，1998，3(4)：P263．
[47]周锐，杨涤 复杂背景中目标图像中的提取与跟踪．系统工程与电子技术，1997
[48]周志明，汪亚明 基于运动区域的多目标检测．计算机测量与控制，2002，10(7)
[49]张嫣，姚耀文 运动图像序列中多目标跟踪的研究与实现．计算机应用研究 2002：P74．
[50]徐毓，李锋，金以慧 基于聚类融合的多目标跟踪算法．传感器技术，2002，21(7)：P31
[51]B.COIFMAN, D.BEYMER, EMCLAUCHLAN, A real-time computer vision system for vehicle tracking and traffic surveillance[J].Transportation Research Part C, 1998, 6: P271-288.
[52]J. FERRU, A. OLLERO. Integrated real-time vision system for vehicle control in nonstructured environments. Engineering Applications of Artificial Intelligence[J].2000, 13:P215-236
[53]FRANCOIS G.MEYER, PATRICK BOUTHEMY. Region-based tracking using a fine motion models in long image sequences[J].Computer Vision, Graphics, and lmageprocessing(CVGIP), 1994, 60(2): P119-140.
[54]JORGE BADENAS, F.PLA.Segmentation based on region-tracking in image sequences for traffic monitoring.In 14th international Conference on Pattern
Recognition, ICPR, 1998: P999-1001.-+
[55]D.Beymer and K.Konolige. Real-time tracking of multiple people using stereo.In IEEE Frame Rate Workshop, 1999.
[56]徐大为，顾樑，刘重庆 航拍图像中运动车辆的检测与定位．计算机工程 2002，Vol．28，No．9
[57]刘亚，艾海舟，徐光佑 一种基于背景模型的运动目标检测与跟踪算法．信息与控制 2002，Vol．31，No．4
[58]路迈西，王勇 利用阈值分割技术提取煤泥浮选泡沫图像的物理特征．煤炭科学技术 2002，Vol．30，No．8
[59]A.Bobick and J.Davis. Real-time recognition of activity using temporal templates. In IEEE Workshop on Application of Computer Vision, Pages 1233-1251,1996.
[60]D.Comaniciu, V.Ramesh, P.Meer. Real Time Tracking of Non-Rigid Objects using Mean Shift. In Computer Vision and Pattern Recognition conference, 2000.
[61]史立，张兆扬，马然 基于运动跟踪匹配技术的视频对象提取．通信学报，2001，Vol．22，No．11
[62]余洪山，王耀南 一种新型智能图像监控系统．信号与控制，2002，Vol．31，No．6
[63]白雪生，金国英 基于帧间运动的视频分割．清华大学学报，2002，Vol．42，No．1
[64]张玲华 对有背景的图像实现运动目标的边界检测．南京邮电学院学报，1997，Vol．17，No．3
[65]祝远新，徐光佑 一种基于块匹配的鲁棒运动估计算法．中国图象图形学报，1998，Vol．3，No．9
[66]王亮，胡卫明，谭铁牛 人运动的视觉分析综述．计算机学报，2002，Vol．25，No．3
[67]Cui.Y and Weng.J. Hand segmentation using learning-based prediction and verification for hand sign recognition. In:Proc IEEE Conference on Computer Vision and Pattern Recognition. Puerto Rico. 1997.P88-93.
[68]Haritaoglu I. Harwood D and Davis L.W~4: real-time surveillance of people and their activities.IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
[69]Aggarwal J and Cai Q.Human motion analysis: a review. Computer Vision and
Image Understanding. 1999.73(3): 428-440.
[70]Yang J and Waibel A. A real-time face tracker. In:Proc IEEE Workshop on Applications of Computer Vision. Sarasota.USA. 1996.142-147.
[71]王岩松，阮秋琦 一种基于互相关的图像定位匹配算法研究与应用．北方交通大学学报，2002，Vol．26
[72]刘新海，方康玲 一种基于灰度特征的快速识别定位算法．三峡大学学报，2002，2．
[73]郑江滨，张艳宁，冯大淦 视频监视中运动目标的检测与跟踪算法．系统工程与电子技术，Vol．24，No．10
[74]艾海舟，王拴，何克忠．基于差分图象的人脸检测．中国图象图形学报，1998，3(12)：P987．
[75]杨绍清，贾传荧．基于模糊判决的图象边缘连接．光学技术，2002，3，Vol．28 No．2
[76]王拴，艾海舟，何克忠．基于差分图象的多运动目标的检测与跟踪．中国图象图形学报，1999，4(6)：P470．
[77]罗希平，田捷等．图象分割方法综述．模式识别与人工智能，1999，12(3)：P300
[78]CHEN Xing-zhi, WANG Qing-yang. Image Motion Detect And Digital Store System. Technology of TV. 1998, (7):23～26(ch).
[79]张有为 维纳与卡尔曼滤波理论导论 北京：人民教育出版社，1980．