复杂环境下运动目标的检测与跟踪
|
摘要
运动目标的检测和跟踪是计算机视觉、图像处理、模式识别等多领域共同研究的热门课题,近些年来已经取得的很多成果,被广泛地应用到军事导航、监控监视、医学诊断、视频检索等众多领域。在军事侦查等条件下环境复杂多变,目标纷繁多样,出没突然缺乏规律可循,所以侦查监视系统要以稳健的目标检测与跟踪算法为核心。本文重点探讨了复杂背景下运动目标检测和跟踪的方法。主要工作和贡献如下:
1、研究了静态背景下目标检测方法和背景模型生成算法。分析了一种基于LBP纹理描述的背景建模方法,应用改进的LBP直方图对背景建模,收到较好的检测效果;通过试验分析了传统目标检测算法的特点,并对部分算法做出了相应改进。最后依据已经分析的目标检测算法的优缺点,采用一种基于对称差分和背景差分的综合运动检测算法,将对称差和多高斯背景以及单高斯背景检测结果进行了有效结合,以提高目标检测的完整性,克服了运动目标短暂滞留的漏检问题。
2、研究了一种基于卡尔曼滤波的跟踪方法。分析了目标匹配算法、卡尔曼滤波和均值偏移算法,特别是卡尔曼滤波和均值偏移算法的理论基础及其在目标跟踪过程中的应用,并做出了对应跟踪方法的具体实现。
3、研究了抗遮挡的目标跟踪方法。改进了一种基于运动预测的均值偏移跟踪算法,根据跟踪过程中运动目标受到遮挡与否,采用不同处理策略将卡尔曼滤波和均值偏移两种算法协同完成跟踪任务,该方法引入颜色和LBP纹理联合直方图的目标建模方法,代替原算法纯粹的颜色直方图建模方法,并引进目标的时空运动位置信息,从而提高了遮挡条件下目标跟踪的鲁棒性。最后研究了一种基于均值偏移的粒子滤波算法,采用颜色和LBP纹理联合直方图对目标建模,建立具有一定自适应能力的动态系统模型,通过均值偏移对粒子的一步迭代,使粒子相对聚类到高概率位置,达到了减少粒子数目提高算法实时性的目的。
The detection and tracking of moving object is a very popular subject in the area of Compute Vision、Image Processing、Pattern Recognition and etc, Lots of achievements had been made in recent years. It has been widely applied in military missile guidance、monitor and surveillances medical diagnosing、video retrieval and other fields. And that under the condition of battleground, the environment is very complex and varied , there are kinds of targets that appear and disappear with few rules. So the kernel of monitor and surveillance system is the robust algorithms of moving target detection and tracking. The paper mainly probe into methods of detection and tracking in complex environment. The major works and innovation of this paper include:
1、Studying moving target detection and Background Model built under static background. We analyze the character of each algorithm in target detection by experiment, some algorithms have been improved. Paper improved a novel algorithm of background model based on LBP texture, and getting a well detecting result. Aimed at the advantage and disadvantage of each method on target detection analyzed before, we adopt an integrated detecting method combined the Symmetrical difference and Background Subtraction in the moving region. Using Symmetrical difference、Multi-gauss Background and Single-Gauss Background combined availably, improved the integrality of detection, conquered the miscarriage of justice of target's whistle stop.
2、Studing a tracking method based kalman filtering. Analyzing target matching、kalman filtering and mean shift algorithms, Particularly the wide application in moving object tracking of kalman filtering and mean shift. Then realized the correlative tracking methods of them.
3、Studying the moving target tracking methods resisting the occlusion. An improved mean shift algorithm based on moving prediction has been proposed, which import target modeled with color and LBP texture united histogram, using real-time object's position information to make target tracking more robust. Lastly paper propose an improved particle filtering algorithm based on mean shift, which adopt color and LBP texture united histogram-based target model, build a self- adaptively dynamic system model, use mean shift iterative to every particle to high probability position, so that reducing the number of particles and improving the real-time quality.
1、研究了静态背景下目标检测方法和背景模型生成算法。分析了一种基于LBP纹理描述的背景建模方法,应用改进的LBP直方图对背景建模,收到较好的检测效果;通过试验分析了传统目标检测算法的特点,并对部分算法做出了相应改进。最后依据已经分析的目标检测算法的优缺点,采用一种基于对称差分和背景差分的综合运动检测算法,将对称差和多高斯背景以及单高斯背景检测结果进行了有效结合,以提高目标检测的完整性,克服了运动目标短暂滞留的漏检问题。
2、研究了一种基于卡尔曼滤波的跟踪方法。分析了目标匹配算法、卡尔曼滤波和均值偏移算法,特别是卡尔曼滤波和均值偏移算法的理论基础及其在目标跟踪过程中的应用,并做出了对应跟踪方法的具体实现。
3、研究了抗遮挡的目标跟踪方法。改进了一种基于运动预测的均值偏移跟踪算法,根据跟踪过程中运动目标受到遮挡与否,采用不同处理策略将卡尔曼滤波和均值偏移两种算法协同完成跟踪任务,该方法引入颜色和LBP纹理联合直方图的目标建模方法,代替原算法纯粹的颜色直方图建模方法,并引进目标的时空运动位置信息,从而提高了遮挡条件下目标跟踪的鲁棒性。最后研究了一种基于均值偏移的粒子滤波算法,采用颜色和LBP纹理联合直方图对目标建模,建立具有一定自适应能力的动态系统模型,通过均值偏移对粒子的一步迭代,使粒子相对聚类到高概率位置,达到了减少粒子数目提高算法实时性的目的。
The detection and tracking of moving object is a very popular subject in the area of Compute Vision、Image Processing、Pattern Recognition and etc, Lots of achievements had been made in recent years. It has been widely applied in military missile guidance、monitor and surveillances medical diagnosing、video retrieval and other fields. And that under the condition of battleground, the environment is very complex and varied , there are kinds of targets that appear and disappear with few rules. So the kernel of monitor and surveillance system is the robust algorithms of moving target detection and tracking. The paper mainly probe into methods of detection and tracking in complex environment. The major works and innovation of this paper include:
1、Studying moving target detection and Background Model built under static background. We analyze the character of each algorithm in target detection by experiment, some algorithms have been improved. Paper improved a novel algorithm of background model based on LBP texture, and getting a well detecting result. Aimed at the advantage and disadvantage of each method on target detection analyzed before, we adopt an integrated detecting method combined the Symmetrical difference and Background Subtraction in the moving region. Using Symmetrical difference、Multi-gauss Background and Single-Gauss Background combined availably, improved the integrality of detection, conquered the miscarriage of justice of target's whistle stop.
2、Studing a tracking method based kalman filtering. Analyzing target matching、kalman filtering and mean shift algorithms, Particularly the wide application in moving object tracking of kalman filtering and mean shift. Then realized the correlative tracking methods of them.
3、Studying the moving target tracking methods resisting the occlusion. An improved mean shift algorithm based on moving prediction has been proposed, which import target modeled with color and LBP texture united histogram, using real-time object's position information to make target tracking more robust. Lastly paper propose an improved particle filtering algorithm based on mean shift, which adopt color and LBP texture united histogram-based target model, build a self- adaptively dynamic system model, use mean shift iterative to every particle to high probability position, so that reducing the number of particles and improving the real-time quality.
引文
[1]阮秋琦,阮宇智,数字图像处理(第二版)[M],北京:电子工业出版社,2003:460-514
[2]章毓晋,图象分割[M],北京:科学出版社,2001:149-172
[3]王新成,高级图像处理技术[M],北京:中国科学技术出版社,2001:14-26
[4]付梦印,邓志红,kalman滤波理论及其在导航系统中的应用[M],北京:科学出版社,2003:1-86
[5]刘皓挺,杨建群,徐风刚,基于运动与区域信息的移动机器人目标检测[J],计算机工程,2007.33(21):205-209
[6]Collins Robert T,Lipton Alan J,A system for video sruveillance and monitoring[A].Proceedings of the American Nuclear Society(ANS)Eighth International Topical Meeting on Robotics and Remote Systems,1999:25-29
[7]李文斌,周晓敏,王长松,一种基于背景减法的运动目标检测算法[J],北京科技大学学报,2008.30(2):212-216
[8]Haritaoglu I,Harwood D,W4:Real-time surveillance of people and their activities[J].IEEE Transactions Pattern Analysis and Machine Intelligence,2000.22(8):809-830
[9]Ridder C,Munkelt O,Kirchner H.Adaptive background estimation and foreground detection using Kalman-filtering[A].Proceedings of International Conference on recent Advances in Macaronis[C].1995.1:193-199
[10]D.Meyer,J.Denzter,H.Niemann,Model based extraction of articulated objects in image sequences for gait analysis.Proceedings of the IEEE International Conference on Image Processing,1997.(3):78-81
[11]Jang D-S,Choi H-I,Active models for tracking[J].Pattern Recognition,2005.33(7):1135-1146
[12]Paragios N,Deriche R,Geodesic active contours and level sets for the detection and tracking of moving objects[J].IEEE Transactions of Pattern Analysis and Machine Intelligence,2000.22(3):266-280
[13]Watcher S,Nagel H-H,Tracking persons in monocular image sequences[J].Compute Vision and Image Understanding.1999.74(5):174-192
[14]贺贵明,李凌娟,一种快速的基于对称差分的视频分割算法[J],小型微型计算机系统,2003.24(6):966-968
[15]张春玲,图像的阈值分割及其应用[J],泰山医学院学报,2006.27(3):84-88
[16]孔明,孙希平,一种改进的基于类间方差的阈值分割法[J],华中科大学报,2004.32(7):46--47
[17]田俊霞,穆国燕、陈树中,基于边界特征的一维最大熵图象分割算法的研究与实现[J],计算机工程与科学,2002.24(6):46-48
[18]林洪文,涂丹,李国辉,基于统计背景模型的运动检测方法[J],计算机工程,2002.29(16):97-99
[19]马义德,朱望飞,改进的基于高斯混合模型的运动目标检测方法[J],计算机应用,2007.27(10):2544-2546
[20]M.Heikkila and M.Pietikainen,A Texture-Based Method for Modeling the Background and Detecting Moving Objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006.28(4):652-657
[21]宁纪锋,吴成柯,一种基于纹理模型的Meanshift目标跟踪算法[J],模式识别与人工智能,2007.20(5):612-618
[22]周西汉,刘勃,周荷琴,一种基于对称差分和背景消减的运动检测方法[J],计算机仿真,2005.22(4):117-119
[23]余静,游志胜,自动目标识别与跟踪技术研究综述[J],计算机应用研究,2005.1:12-15
[24]D.A.Montera,S.K.Rogers,D.W.Ruck,W.Dermis,M.E.Oxley.Object tracking through adaptive correlation[J].Optical Engineering,1994.33(1):294-302.
[25]张江山,朱光喜,一种基于Kalman滤波的视频对象跟踪方法[J],中国图像图形学报,2002.7A(6):606-609
[26]E.Loutast,K.Diamantarast,LPitast.Occlusion resistant object tracking[A].IEEE International Conference on Image Processing[C].Thessaloniki,Greece,2001:65-68.
[27]Hieu T.Nguyen,Mazcel Worring,Rein van den Boomgaard,Occlusion robust adaptive template tracking[A].Proceedings of Eighth IEEE International Conference on Computer Vision[C],Vancouver,Canada,2001:678-683.
[28]Ken Ito,Shigeyuki Sakane.Robust view-based visual tracking with detection of occlusions[A].IEEE International Conference on Robotics and Automation[C],Seoul,Korea,2001:1207-1213.
[29]K.Nummiaro,E.Koller-Meier,L.Van Gool.An adaptive color-based particle filter[J].Image and Vision Computing.2003,21(1):99-110.
[30]李培华,一种改进的Mean Shift跟踪算法[J],自动化学报,2007.33(4):347-354
[31]石华伟,夏利民,基于Mean Shift算法和粒子滤波器的人眼跟踪[J],计算机工程与应用,2006.19:26-28
[32]常发亮,刘雪,王华杰,基于均值漂移与卡尔曼滤波的目标跟踪算法[J],计算机工程与应用 2007.43(12):50-53
[33]朱胜利,朱善安,李旭超,快速运动目标的Mean shift跟踪算法[J],光电工程 2006.33(5):66-70
[34]J.S.Liu and R.chen.Sequential Monte Carlo Methods for Dynamic Systems[J]Journal of the American Statistical Association.1998,93(443):1032-1044.
[35]Canfeng Shan,Yucheng Wei,Tieniu Tan,Frederic Ojardias.Real time hand tracking by combining particle filtering and mean shift[A].Sixth IEEE International Conference on Automatic Face and Gesture Recognition[C],Seoul,Korea,2004:669-674.
[36]Cheng Chang,Rashid Ansad.Kernel particle filter for visual tracking[J].IEEE Signal Processing Lettters.2005,12(3):242-245.
[37]Koichir Deguehi,Oki Kawanaka,Takayuki Okatani.Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithm[A].International Conference on Pattern Recognition[C],Cambridge,England,UK,2004:506-509.
[38]郑江宾,视频监视方法研究[D],博士论文 西北工业大学,2002.5
[39]邵叶秦,基于序列图像的人头定位[D],硕士论文 南京理工大学,模式识别与智能系统,2004.6
[40]王宾,视频序列中运动目标检测与跟踪有关问题的研究[D],硕士论文,西北大学电子系,2004
[41]陈阳,基于视频的交通参数采集系统的研究与实现[D],硕士论文,西北大学,2005
[42]彭宁嵩,Mean-Shift可视跟踪中的稳健性研究[D],博士论文,上海交通大学,2005
[43]朱胜利,Mean Shift及相关算法在视频跟踪中的研究[D],博士论文,浙江大学控制理论与控制工程,2006
[2]章毓晋,图象分割[M],北京:科学出版社,2001:149-172
[3]王新成,高级图像处理技术[M],北京:中国科学技术出版社,2001:14-26
[4]付梦印,邓志红,kalman滤波理论及其在导航系统中的应用[M],北京:科学出版社,2003:1-86
[5]刘皓挺,杨建群,徐风刚,基于运动与区域信息的移动机器人目标检测[J],计算机工程,2007.33(21):205-209
[6]Collins Robert T,Lipton Alan J,A system for video sruveillance and monitoring[A].Proceedings of the American Nuclear Society(ANS)Eighth International Topical Meeting on Robotics and Remote Systems,1999:25-29
[7]李文斌,周晓敏,王长松,一种基于背景减法的运动目标检测算法[J],北京科技大学学报,2008.30(2):212-216
[8]Haritaoglu I,Harwood D,W4:Real-time surveillance of people and their activities[J].IEEE Transactions Pattern Analysis and Machine Intelligence,2000.22(8):809-830
[9]Ridder C,Munkelt O,Kirchner H.Adaptive background estimation and foreground detection using Kalman-filtering[A].Proceedings of International Conference on recent Advances in Macaronis[C].1995.1:193-199
[10]D.Meyer,J.Denzter,H.Niemann,Model based extraction of articulated objects in image sequences for gait analysis.Proceedings of the IEEE International Conference on Image Processing,1997.(3):78-81
[11]Jang D-S,Choi H-I,Active models for tracking[J].Pattern Recognition,2005.33(7):1135-1146
[12]Paragios N,Deriche R,Geodesic active contours and level sets for the detection and tracking of moving objects[J].IEEE Transactions of Pattern Analysis and Machine Intelligence,2000.22(3):266-280
[13]Watcher S,Nagel H-H,Tracking persons in monocular image sequences[J].Compute Vision and Image Understanding.1999.74(5):174-192
[14]贺贵明,李凌娟,一种快速的基于对称差分的视频分割算法[J],小型微型计算机系统,2003.24(6):966-968
[15]张春玲,图像的阈值分割及其应用[J],泰山医学院学报,2006.27(3):84-88
[16]孔明,孙希平,一种改进的基于类间方差的阈值分割法[J],华中科大学报,2004.32(7):46--47
[17]田俊霞,穆国燕、陈树中,基于边界特征的一维最大熵图象分割算法的研究与实现[J],计算机工程与科学,2002.24(6):46-48
[18]林洪文,涂丹,李国辉,基于统计背景模型的运动检测方法[J],计算机工程,2002.29(16):97-99
[19]马义德,朱望飞,改进的基于高斯混合模型的运动目标检测方法[J],计算机应用,2007.27(10):2544-2546
[20]M.Heikkila and M.Pietikainen,A Texture-Based Method for Modeling the Background and Detecting Moving Objects[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006.28(4):652-657
[21]宁纪锋,吴成柯,一种基于纹理模型的Meanshift目标跟踪算法[J],模式识别与人工智能,2007.20(5):612-618
[22]周西汉,刘勃,周荷琴,一种基于对称差分和背景消减的运动检测方法[J],计算机仿真,2005.22(4):117-119
[23]余静,游志胜,自动目标识别与跟踪技术研究综述[J],计算机应用研究,2005.1:12-15
[24]D.A.Montera,S.K.Rogers,D.W.Ruck,W.Dermis,M.E.Oxley.Object tracking through adaptive correlation[J].Optical Engineering,1994.33(1):294-302.
[25]张江山,朱光喜,一种基于Kalman滤波的视频对象跟踪方法[J],中国图像图形学报,2002.7A(6):606-609
[26]E.Loutast,K.Diamantarast,LPitast.Occlusion resistant object tracking[A].IEEE International Conference on Image Processing[C].Thessaloniki,Greece,2001:65-68.
[27]Hieu T.Nguyen,Mazcel Worring,Rein van den Boomgaard,Occlusion robust adaptive template tracking[A].Proceedings of Eighth IEEE International Conference on Computer Vision[C],Vancouver,Canada,2001:678-683.
[28]Ken Ito,Shigeyuki Sakane.Robust view-based visual tracking with detection of occlusions[A].IEEE International Conference on Robotics and Automation[C],Seoul,Korea,2001:1207-1213.
[29]K.Nummiaro,E.Koller-Meier,L.Van Gool.An adaptive color-based particle filter[J].Image and Vision Computing.2003,21(1):99-110.
[30]李培华,一种改进的Mean Shift跟踪算法[J],自动化学报,2007.33(4):347-354
[31]石华伟,夏利民,基于Mean Shift算法和粒子滤波器的人眼跟踪[J],计算机工程与应用,2006.19:26-28
[32]常发亮,刘雪,王华杰,基于均值漂移与卡尔曼滤波的目标跟踪算法[J],计算机工程与应用 2007.43(12):50-53
[33]朱胜利,朱善安,李旭超,快速运动目标的Mean shift跟踪算法[J],光电工程 2006.33(5):66-70
[34]J.S.Liu and R.chen.Sequential Monte Carlo Methods for Dynamic Systems[J]Journal of the American Statistical Association.1998,93(443):1032-1044.
[35]Canfeng Shan,Yucheng Wei,Tieniu Tan,Frederic Ojardias.Real time hand tracking by combining particle filtering and mean shift[A].Sixth IEEE International Conference on Automatic Face and Gesture Recognition[C],Seoul,Korea,2004:669-674.
[36]Cheng Chang,Rashid Ansad.Kernel particle filter for visual tracking[J].IEEE Signal Processing Lettters.2005,12(3):242-245.
[37]Koichir Deguehi,Oki Kawanaka,Takayuki Okatani.Object tracking by the mean-shift of regional color distribution combined with the particle-filter algorithm[A].International Conference on Pattern Recognition[C],Cambridge,England,UK,2004:506-509.
[38]郑江宾,视频监视方法研究[D],博士论文 西北工业大学,2002.5
[39]邵叶秦,基于序列图像的人头定位[D],硕士论文 南京理工大学,模式识别与智能系统,2004.6
[40]王宾,视频序列中运动目标检测与跟踪有关问题的研究[D],硕士论文,西北大学电子系,2004
[41]陈阳,基于视频的交通参数采集系统的研究与实现[D],硕士论文,西北大学,2005
[42]彭宁嵩,Mean-Shift可视跟踪中的稳健性研究[D],博士论文,上海交通大学,2005
[43]朱胜利,Mean Shift及相关算法在视频跟踪中的研究[D],博士论文,浙江大学控制理论与控制工程,2006