刚性运动目标的跟踪算法研究
|
摘要
运动目标跟踪在军事视觉制导、机器人视觉导航、工业产品检测、医疗诊断、交通监视等领域均有重要的实用价值和广阔的发展前景。由于被跟踪目标本身特征的多样性、所处环境的复杂性,使目标跟踪成为挑战性的课题,特别是跟踪过程中出现的遮挡问题成为限制跟踪算法鲁棒性的关键因素。
本文主要针对刚性运动目标的跟踪问题进行研究,详细讨论了基于边缘特征的刚性运动目标跟踪算法。在该基础上,又进一步讨论遮挡情况下的边缘匹配和灰度匹配算法,论文的主要工作有:
1、刚性目标的轮廓线或边界线是视觉感知与理解的重要线索或特征,采用帧间图像差分法进行运动目标检测,利用随机边缘特征有效地对目标进行跟踪,该算法对目标的视角、光线及运动状态的变化等不利因素有较好的适应性。
2、针对刚性运动目标跟踪中的遮挡问题,提出边缘匹配和灰度相关匹配的跟踪算法。目标灰度单一时采用边缘匹配算法,目标灰度丰富时采用灰度相关匹配算法。对目标自适应分块,使各子块具有较明显的特征,增加遮挡判定和子块匹配的置信度;然后通过各子块来准确判定被遮挡区域,在遮挡情况下利用剩余的未被遮挡的子块进行灰度相关匹配和表决,在目标被完全遮挡情况下利用Kalman预测进行跟踪。该算法对于刚性目标的跟踪具有很好的实时性和跟踪精度。
Moving target tracking plays an important role in military visual missile guidance, robot vision navigation, industrial product inspection, medical diagnosing and traffic surveillance, etc. Due to the facts of variety of the feature of the targets, the complexity of the environmental background, moving target tracking is a challenging subject. Especially the occlusion problem in the course of tracking has been one of the crucial restrictive factors to the robustness of the tracking algorithms.
This thesis mainly focuses on the tracking of rigid moving targets. It detailedly discussed the tracking algorithm based on edge-feature-matching, particle filter and intensity-correlation-matching algorithms under occlusion.
The major contribution can be summarized as follows:
1. The contour line or the border line of the rigid target is the important clue and feature for visual sense. Two consecutive frames subtraction is applied to detecting the moving objects and random edge feature is contributed to object tracking. The algorithm can adapt well to the disadvantageous factors such as angles of target point, rays, and moving states of targets.
2. Aiming at the general tracking of rigid targets under occlusion, we proposed a tracking algorithm based on edge and intensity matching. Edge matching algorithm is applied when the intensity of target is uniform, while intensity matching algorithm is applied when the intensity information is abundant. The target is adaptively divided in order to make each block with distinct feature to increase the accuracy degree of occlusion estimating and block matching. Then through blocks, the occlusion regions are accurately estimated, and match and vote are made using the remaining un-occluded blocks. Kalman prediction is used to track when full occlusion happens. This algorithm can track rigid target accurately and real-time.
本文主要针对刚性运动目标的跟踪问题进行研究,详细讨论了基于边缘特征的刚性运动目标跟踪算法。在该基础上,又进一步讨论遮挡情况下的边缘匹配和灰度匹配算法,论文的主要工作有:
1、刚性目标的轮廓线或边界线是视觉感知与理解的重要线索或特征,采用帧间图像差分法进行运动目标检测,利用随机边缘特征有效地对目标进行跟踪,该算法对目标的视角、光线及运动状态的变化等不利因素有较好的适应性。
2、针对刚性运动目标跟踪中的遮挡问题,提出边缘匹配和灰度相关匹配的跟踪算法。目标灰度单一时采用边缘匹配算法,目标灰度丰富时采用灰度相关匹配算法。对目标自适应分块,使各子块具有较明显的特征,增加遮挡判定和子块匹配的置信度;然后通过各子块来准确判定被遮挡区域,在遮挡情况下利用剩余的未被遮挡的子块进行灰度相关匹配和表决,在目标被完全遮挡情况下利用Kalman预测进行跟踪。该算法对于刚性目标的跟踪具有很好的实时性和跟踪精度。
Moving target tracking plays an important role in military visual missile guidance, robot vision navigation, industrial product inspection, medical diagnosing and traffic surveillance, etc. Due to the facts of variety of the feature of the targets, the complexity of the environmental background, moving target tracking is a challenging subject. Especially the occlusion problem in the course of tracking has been one of the crucial restrictive factors to the robustness of the tracking algorithms.
This thesis mainly focuses on the tracking of rigid moving targets. It detailedly discussed the tracking algorithm based on edge-feature-matching, particle filter and intensity-correlation-matching algorithms under occlusion.
The major contribution can be summarized as follows:
1. The contour line or the border line of the rigid target is the important clue and feature for visual sense. Two consecutive frames subtraction is applied to detecting the moving objects and random edge feature is contributed to object tracking. The algorithm can adapt well to the disadvantageous factors such as angles of target point, rays, and moving states of targets.
2. Aiming at the general tracking of rigid targets under occlusion, we proposed a tracking algorithm based on edge and intensity matching. Edge matching algorithm is applied when the intensity of target is uniform, while intensity matching algorithm is applied when the intensity information is abundant. The target is adaptively divided in order to make each block with distinct feature to increase the accuracy degree of occlusion estimating and block matching. Then through blocks, the occlusion regions are accurately estimated, and match and vote are made using the remaining un-occluded blocks. Kalman prediction is used to track when full occlusion happens. This algorithm can track rigid target accurately and real-time.
引文
[1]Lipton,A.J.Fujiyoshi,H.Patil,R S.,Moving Target Classification and Tracking from Real-time Video.Proceeding of Fourth IEEE Workshop on Applications of Computer Vision,WACV' 98:8-14.
[2]Amidi,O.Kanade,T.Fujita,K.A visual odometer for autonomous helicopter fight.Proceedings of the Fifth International Conference on Intelligent Autonomous Systems(IAS-5),June,1998.
[3]Nordlund,P.Uhlin,T.Closing the loop:Detection and pursuit of a moving object by a moving observer[J].Image and Vision computing,1996.14(4):265-275.
[4]Collins,R.T.Lipton,A.J.Kanade,T.etc.A System for Video Surveillance and Monitoring.USA:Robotics Institute,Carnegie Mellon University,(2000-05-11).
[5]刘亚,艾海舟,徐光佑.基于主运动分析的野外视觉侦察系统—运动目标检测、跟踪及全景图的生成[J].机器人,2001.23(3):250-255.
[6]汪建华,赵晓光,谭民.一种5自由度视觉伺服机器人的跟踪控制研究[J].机器人,2005.27(3):215-219.
[7]Liu,G.Y.Chen,R.Deng,Y.etc.Video-based 3D human body motion capture.Journal of Computer-Aided Design and Computer Graphics,2006.18(1):82-88.
[8]Kim,Z.Malik,J.Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking.Proceedings.Ninth IEEE International Conference on Computer Vision,2003:524-531.
[9]Zhu,E.Yin,J.P.Zhang,G.M.Fingerprint matching based on the transference of reference minutiae.Journal of Najing University(Natural Sciences),2005.41(4):424-428.
[10]Zhong,Y.Jain,A.and Dubuisson-Jolly M.Object tracking using deformable templates.IEEE Trans Pattern Analysis and Machine Intelligence,2000.22(5):544-549.
[11]Dae-Sik Jang and Hyung-ll Choi,Active models for tracking moving objects.Pattern Recognition,2000.33(7):1135-1146.
[12]Gupte,S.Masoud,O.Martin,R.F.K.etc.Detection and classification of vehicles.IEEE Transactions on Intelligent Transportation Systems,2002.3(1):37-47.
[13]McKenna,S.Tracking groups of people.Computer Vision and Image Understanding,2000.80(1):42-56.
[14]Osama,M.Nikolaos,P.P.A novel method for tracking and counting pedestrians in real-time using a single camera.IEEE Transactions on Vehicular Technology,2001.50(5):1267-1277.
[15]Chang Faliang,Ma Li,Qiao Yizheng,Target Tracking Under Occlusion by Combining Integral-Intensity-Matching with Multi-block-voting.Lecture notes in computer science,Springer,2005.3644(1):77-86.
[16]Oberti,F.Calcagno,S.Zara,M.and Regazzoni,C.S.Robust tracking of humans and vehicles in cluttered scenes with occlusions[A].IEEE International Conference on Image Processing[C],2002.6:629-632.
[17]Ito,K.Sakane,S.Robust view-based visual tracking with detection of occlusions[A].IEEE International Conference on Robotics and Automation[C],Seoul,Korea,2001:1207-1213.
[18]Kamijo,S.Matsushita,Y.Ikeuchi,K.Sakauchi,M.Occlusion robust tracking utilizing spatio-temporal markov random field model[A].Proceedings of 15th International Conference on Pattern Recognition[C],Barcelona,Spain,2000:140-144.
[19]Y.Wu,T.Yu,G.Hua,Tracking appearances with occlusion.Proc IEEE conf on computer Vision and Pattern Recognition,Madison,USA,2003:789-795.
[20]Katja Nummiaro,Esther Koller-Meier and Luc Van Gool.An adaptive color-based particle filter.Image and Vision Computing,2003.1:99-110.
[21]Jian-Wei Zhao,Peng Wang,Chong-Qing Liu,An object tracking algorithm based on occlusion mesh model.Proceedings of 2002 International Conference on machine learning and cybernetics,2002:288-292.
[22]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(4).
[23]C.Stauffer,W.Grimson,Learning patterns of activity using realtime tracking.IEEE Trans.Pattern Anal.Machine Intell.22(August 2000):747-757.
[24]贺贵明,李凌娟,贾振堂,一种快速的基于对称差分的视频分割算法.小型微型计算机系统,2003(6):966-968.
[25]赵建云,郑晓势,周伟,刘广起,基于视频的车辆检测与跟踪技术综述.计算机与信息技术,计算机与信息技术,2007(4):30-33.
[26]L.Marcenaro,M.Ferrari,L.Marchesotti,etc.Multiple Object Tracking under Heavy Occlusions by Using Kalman Filters Based on Shape Matching[C].International Conference on Image Processing,2002:341-344.
[27]陈忠碧,张启衡,一种适合于多目标检测的图像分割方法.光电工程,2004.5:34-37.
[28]张桂林,张天庠,魏洛刚,谢先明,基于边缘特征的运动目标提取与跟踪.华中理工大学学报,1994.5(22):42-45.
[29]William K.Pratt,Digital Image Processing.New York:John Wiley &Sons,1991.
[30]Y.Gemignani,M.Paterni,A.Benassi and M.Demi,Real time contour tracking with a new edge detector.Real-Time Imaging,2004.4:103-116.
[31]Enkelman,W.Investigations of Multigrid Algorithms for the Estimation of Optical flow Fields in Images Sequences.Computer Vision,Graphics and Image Processing,1998(43):150-177.
[32]吕海霞,陈红林,改进的SUSAN角点提取算法.电光与控制,2008.5:45-48.
[33]沈美丽,宋华军,基于角点检测的光流目标跟踪算法.电子器件,2007.8:1397-1399.
[34]李会猛,陈家乾,诸静,基于自适应颜色识别技术的快速多目标跟踪方法.计算机工程与应用,2005(30):60-62.
[35]刘友明,刘希顺,刘安之,王博亮,一种基于LUV均匀颜色空间的彩色分割方法.微型电脑应用,2000(16):27-28.
[36]赵春晖,张洪才,王永忠,基于特征颜色空间变换的目标跟踪融合算法.计算机工程与应用,2008.44(3):8-9.
[37]Peterfreund,N.Robust tracking of position and velocity with Kalman snakes[J].IEEE Transactions on Patteran Analysis and Machine Intelligence. 2000.22(6):564-569.
[38]M.Kass,A.P.Witkin,D.Terzopoulos.Snake:active contour models [J].International Journal of Computer Vision.1998:321-331.
[39]S.X.Ju,M.J.Blacky,Y.Yacoobz,Cardboard people:A parameterizedmodel of articulated image motion,in:Proc.Int.Conf.Automatic Face and Gesture Recognition,Killington,Vermont,1996,pp.38-44.
[40]孙怡,王恩亮,安宏杰,胡家升,基于2-D模型的人体运动跟踪.中国图象图形学报,2002.7(7):625-632.
[41]Lars Bretzner,Multi-Scale Feature Tracking and Motion Estimation,Computational Vision and Active Perception Laboratory,October 1999.
[42]洪宇,高广珠,余理富,何智勇,随机边缘特征匹配在运动车辆跟踪算法中的应用.计算机工程与科学,2005(27):35-37.
[43]刘贵喜,邵明礼,刘先红,朱东波,真实场景下视频运动目标自动提取方法.光学学报,2006.8:1150-1155.
[44]宋光乐,高斯噪声线性滤波问题研究.临沂师范学院学报,2001.12:21-24.
[45]张传生,数字通信原理[M].西安:西安交大出版社,1990.
[46]阮沈勇、王永利、桑群芳,MATLAB程序设计[M].北京:电子工业出版社,2004.
[47]T.Murugas,R.Peplow,J.R.Tapamo,Extraction of an object model for video tracking[C].IEEE African Conference in Africa,George,South Africa,2002.1:317-322.
[48]章毓晋,图像处理和分析[M].北京:清华大学出版社,1999.
[49]孙莹涛、李玉山,多运动目标跟踪及连通域标记方法.电子元器件应用,2007.5:44-48.
[50]刘峰、庄越挺、罗忠祥、潘云鹤,采用弱预测机制的人体运动跟踪算法.中国图像图形学报,<第8卷(A版)第4期>2003年4月.
[51]Byung-Gyu Kim,Do-Jong Kim,Dong-Jo Park,Novel precision target detection with adaptive thresholding or dynamic image segmentation.Machine Vision and Application(2001)12:259-270.
[52]陆宗骐、梁诚,用Sobel算子细化边缘[J].中国图象图形学报,2000.(6):516-520.
[53]王爱民、赵忠旭、沈兰荪.基于矢量Prewitt算子的多尺度彩色图像边缘检测方法[J].中国图象图形学报,1999.(12):1024-1028.
[54]陈莹、韩崇昭,运动车辆的多传感融合跟踪.西安交通大学学报,2004.10:1035-1039.
[55]WREN C,AZARBAYEJANI A,DARRELL T,etc.Pfinder:Real-time tracking of the human body[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997.19(7):780-?85.
[56]Marecenaro L,Ferrari M,Marchesottl L,Multiple object tracking under heavy occlusions by using kalman filter based on shape matching[A].IEEE International Conference on Image Processing[C],Rochester,New York,USA,2002:341-344.
[57]杨振亚、白治江、王成道,自适应Canny边缘检测算法.上海海运学院学报,2003.12:373-377.
[58]朱立新、夏德深,目标自适应图像分块与小目标提取.计算机工程与应用,2005.25:88-90.
[59]常发亮、马丽、乔谊正,遮挡情况下基于特征相关匹配的目标跟踪算法.中国图象图形学报,2006.12:877-882.
[60]刘静、王军宁、范乐伟,基于模板修正和自适应Kalman预测的刚性目标跟踪.现代电子技术,2008(3):154-157.
[2]Amidi,O.Kanade,T.Fujita,K.A visual odometer for autonomous helicopter fight.Proceedings of the Fifth International Conference on Intelligent Autonomous Systems(IAS-5),June,1998.
[3]Nordlund,P.Uhlin,T.Closing the loop:Detection and pursuit of a moving object by a moving observer[J].Image and Vision computing,1996.14(4):265-275.
[4]Collins,R.T.Lipton,A.J.Kanade,T.etc.A System for Video Surveillance and Monitoring.USA:Robotics Institute,Carnegie Mellon University,(2000-05-11).
[5]刘亚,艾海舟,徐光佑.基于主运动分析的野外视觉侦察系统—运动目标检测、跟踪及全景图的生成[J].机器人,2001.23(3):250-255.
[6]汪建华,赵晓光,谭民.一种5自由度视觉伺服机器人的跟踪控制研究[J].机器人,2005.27(3):215-219.
[7]Liu,G.Y.Chen,R.Deng,Y.etc.Video-based 3D human body motion capture.Journal of Computer-Aided Design and Computer Graphics,2006.18(1):82-88.
[8]Kim,Z.Malik,J.Fast vehicle detection with probabilistic feature grouping and its application to vehicle tracking.Proceedings.Ninth IEEE International Conference on Computer Vision,2003:524-531.
[9]Zhu,E.Yin,J.P.Zhang,G.M.Fingerprint matching based on the transference of reference minutiae.Journal of Najing University(Natural Sciences),2005.41(4):424-428.
[10]Zhong,Y.Jain,A.and Dubuisson-Jolly M.Object tracking using deformable templates.IEEE Trans Pattern Analysis and Machine Intelligence,2000.22(5):544-549.
[11]Dae-Sik Jang and Hyung-ll Choi,Active models for tracking moving objects.Pattern Recognition,2000.33(7):1135-1146.
[12]Gupte,S.Masoud,O.Martin,R.F.K.etc.Detection and classification of vehicles.IEEE Transactions on Intelligent Transportation Systems,2002.3(1):37-47.
[13]McKenna,S.Tracking groups of people.Computer Vision and Image Understanding,2000.80(1):42-56.
[14]Osama,M.Nikolaos,P.P.A novel method for tracking and counting pedestrians in real-time using a single camera.IEEE Transactions on Vehicular Technology,2001.50(5):1267-1277.
[15]Chang Faliang,Ma Li,Qiao Yizheng,Target Tracking Under Occlusion by Combining Integral-Intensity-Matching with Multi-block-voting.Lecture notes in computer science,Springer,2005.3644(1):77-86.
[16]Oberti,F.Calcagno,S.Zara,M.and Regazzoni,C.S.Robust tracking of humans and vehicles in cluttered scenes with occlusions[A].IEEE International Conference on Image Processing[C],2002.6:629-632.
[17]Ito,K.Sakane,S.Robust view-based visual tracking with detection of occlusions[A].IEEE International Conference on Robotics and Automation[C],Seoul,Korea,2001:1207-1213.
[18]Kamijo,S.Matsushita,Y.Ikeuchi,K.Sakauchi,M.Occlusion robust tracking utilizing spatio-temporal markov random field model[A].Proceedings of 15th International Conference on Pattern Recognition[C],Barcelona,Spain,2000:140-144.
[19]Y.Wu,T.Yu,G.Hua,Tracking appearances with occlusion.Proc IEEE conf on computer Vision and Pattern Recognition,Madison,USA,2003:789-795.
[20]Katja Nummiaro,Esther Koller-Meier and Luc Van Gool.An adaptive color-based particle filter.Image and Vision Computing,2003.1:99-110.
[21]Jian-Wei Zhao,Peng Wang,Chong-Qing Liu,An object tracking algorithm based on occlusion mesh model.Proceedings of 2002 International Conference on machine learning and cybernetics,2002:288-292.
[22]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(4).
[23]C.Stauffer,W.Grimson,Learning patterns of activity using realtime tracking.IEEE Trans.Pattern Anal.Machine Intell.22(August 2000):747-757.
[24]贺贵明,李凌娟,贾振堂,一种快速的基于对称差分的视频分割算法.小型微型计算机系统,2003(6):966-968.
[25]赵建云,郑晓势,周伟,刘广起,基于视频的车辆检测与跟踪技术综述.计算机与信息技术,计算机与信息技术,2007(4):30-33.
[26]L.Marcenaro,M.Ferrari,L.Marchesotti,etc.Multiple Object Tracking under Heavy Occlusions by Using Kalman Filters Based on Shape Matching[C].International Conference on Image Processing,2002:341-344.
[27]陈忠碧,张启衡,一种适合于多目标检测的图像分割方法.光电工程,2004.5:34-37.
[28]张桂林,张天庠,魏洛刚,谢先明,基于边缘特征的运动目标提取与跟踪.华中理工大学学报,1994.5(22):42-45.
[29]William K.Pratt,Digital Image Processing.New York:John Wiley &Sons,1991.
[30]Y.Gemignani,M.Paterni,A.Benassi and M.Demi,Real time contour tracking with a new edge detector.Real-Time Imaging,2004.4:103-116.
[31]Enkelman,W.Investigations of Multigrid Algorithms for the Estimation of Optical flow Fields in Images Sequences.Computer Vision,Graphics and Image Processing,1998(43):150-177.
[32]吕海霞,陈红林,改进的SUSAN角点提取算法.电光与控制,2008.5:45-48.
[33]沈美丽,宋华军,基于角点检测的光流目标跟踪算法.电子器件,2007.8:1397-1399.
[34]李会猛,陈家乾,诸静,基于自适应颜色识别技术的快速多目标跟踪方法.计算机工程与应用,2005(30):60-62.
[35]刘友明,刘希顺,刘安之,王博亮,一种基于LUV均匀颜色空间的彩色分割方法.微型电脑应用,2000(16):27-28.
[36]赵春晖,张洪才,王永忠,基于特征颜色空间变换的目标跟踪融合算法.计算机工程与应用,2008.44(3):8-9.
[37]Peterfreund,N.Robust tracking of position and velocity with Kalman snakes[J].IEEE Transactions on Patteran Analysis and Machine Intelligence. 2000.22(6):564-569.
[38]M.Kass,A.P.Witkin,D.Terzopoulos.Snake:active contour models [J].International Journal of Computer Vision.1998:321-331.
[39]S.X.Ju,M.J.Blacky,Y.Yacoobz,Cardboard people:A parameterizedmodel of articulated image motion,in:Proc.Int.Conf.Automatic Face and Gesture Recognition,Killington,Vermont,1996,pp.38-44.
[40]孙怡,王恩亮,安宏杰,胡家升,基于2-D模型的人体运动跟踪.中国图象图形学报,2002.7(7):625-632.
[41]Lars Bretzner,Multi-Scale Feature Tracking and Motion Estimation,Computational Vision and Active Perception Laboratory,October 1999.
[42]洪宇,高广珠,余理富,何智勇,随机边缘特征匹配在运动车辆跟踪算法中的应用.计算机工程与科学,2005(27):35-37.
[43]刘贵喜,邵明礼,刘先红,朱东波,真实场景下视频运动目标自动提取方法.光学学报,2006.8:1150-1155.
[44]宋光乐,高斯噪声线性滤波问题研究.临沂师范学院学报,2001.12:21-24.
[45]张传生,数字通信原理[M].西安:西安交大出版社,1990.
[46]阮沈勇、王永利、桑群芳,MATLAB程序设计[M].北京:电子工业出版社,2004.
[47]T.Murugas,R.Peplow,J.R.Tapamo,Extraction of an object model for video tracking[C].IEEE African Conference in Africa,George,South Africa,2002.1:317-322.
[48]章毓晋,图像处理和分析[M].北京:清华大学出版社,1999.
[49]孙莹涛、李玉山,多运动目标跟踪及连通域标记方法.电子元器件应用,2007.5:44-48.
[50]刘峰、庄越挺、罗忠祥、潘云鹤,采用弱预测机制的人体运动跟踪算法.中国图像图形学报,<第8卷(A版)第4期>2003年4月.
[51]Byung-Gyu Kim,Do-Jong Kim,Dong-Jo Park,Novel precision target detection with adaptive thresholding or dynamic image segmentation.Machine Vision and Application(2001)12:259-270.
[52]陆宗骐、梁诚,用Sobel算子细化边缘[J].中国图象图形学报,2000.(6):516-520.
[53]王爱民、赵忠旭、沈兰荪.基于矢量Prewitt算子的多尺度彩色图像边缘检测方法[J].中国图象图形学报,1999.(12):1024-1028.
[54]陈莹、韩崇昭,运动车辆的多传感融合跟踪.西安交通大学学报,2004.10:1035-1039.
[55]WREN C,AZARBAYEJANI A,DARRELL T,etc.Pfinder:Real-time tracking of the human body[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997.19(7):780-?85.
[56]Marecenaro L,Ferrari M,Marchesottl L,Multiple object tracking under heavy occlusions by using kalman filter based on shape matching[A].IEEE International Conference on Image Processing[C],Rochester,New York,USA,2002:341-344.
[57]杨振亚、白治江、王成道,自适应Canny边缘检测算法.上海海运学院学报,2003.12:373-377.
[58]朱立新、夏德深,目标自适应图像分块与小目标提取.计算机工程与应用,2005.25:88-90.
[59]常发亮、马丽、乔谊正,遮挡情况下基于特征相关匹配的目标跟踪算法.中国图象图形学报,2006.12:877-882.
[60]刘静、王军宁、范乐伟,基于模板修正和自适应Kalman预测的刚性目标跟踪.现代电子技术,2008(3):154-157.