视频目标阴影消除与跟踪技术研究
|
摘要
视频目标跟踪是计算机视觉、模式识别、人工智能、图像处理等领域的重要研究任务之一。视频目标跟踪,就是通过对摄像机拍摄到的图像序列进行分析,在图像中检测出运动的目标或是用户感兴趣的区域,并在后续帧中估算出目标位置。本文针对静止场景中的目标跟踪,提出了一种结合颜色特征和投影直方图的方法来消除阴影,该方法对被检测为运动目标分别从颜色特征、竖直和水平投影直方图上进行判断；另外,对区域协方差跟踪方法进行了改进,并对目标的进入、离开、合并、分离、遮挡做了相应的处理；设计并开发了视频目标跟踪的实验系统,采用模块化实现。实验结果表明,利用上述方法能够有效地消除运动目标的阴影,并对目标跟踪具有较高的准确性。
Video object tracking is an important task in the fields of computer vision, pattern recognition, artificial intelligence and image processing. Video object tracking analyses the image sequences shoot by camera and detects moving objects or various areas of interest in it, then estimates object locations in subsequent frames. This paper aims at object tracking in static scene, a method using the color feature and project histogram to eliminate shadow is proposed. It processes each detected area separately from the color, vertical, horizontal projection histogram. In addition, the object tracking method based on covariance is improved. Meanwhile, it handles objects entering, leaving, merging, separating and occlusion. Finally, an experimental video object tracking system is designed and developed. It uses modular implementation and achieves good performance. The experimental results show that the above methods eliminate the shadow of moving objects effectively and have higher accuracy in object tracking.
Video object tracking is an important task in the fields of computer vision, pattern recognition, artificial intelligence and image processing. Video object tracking analyses the image sequences shoot by camera and detects moving objects or various areas of interest in it, then estimates object locations in subsequent frames. This paper aims at object tracking in static scene, a method using the color feature and project histogram to eliminate shadow is proposed. It processes each detected area separately from the color, vertical, horizontal projection histogram. In addition, the object tracking method based on covariance is improved. Meanwhile, it handles objects entering, leaving, merging, separating and occlusion. Finally, an experimental video object tracking system is designed and developed. It uses modular implementation and achieves good performance. The experimental results show that the above methods eliminate the shadow of moving objects effectively and have higher accuracy in object tracking.
引文
[1]朱明旱,罗大庸.基于帧间差分背景模型的运动物体检测与跟踪.计算机测量与控制,2006,14 (8):1004～1009
[2]Robert T. Collins, Alan J. Lipton. Introduction to the special section on video surveillance. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):745～746
[3]王智灵,路婷婷,张硕奇.基于全局光流的多目标检测与跟踪.2008系统仿真技术及其应用学术会议,2008,10：265-268
[4]Stauffer C, Grimsonx C. Adaptive Background Mixture Models for Real-time Tracking. In:Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado,1999,2:246～252
[5]Bai Sheng C,Yun Qi L.Indoor and outdoor people detection and shadow suppression by exploiting HSV color information. In:Proceedings of the Fourth International Conference on Computer and InformationTechnology. 2004.137～142
[6]Prati A, Mikic I,Trivedi M,et al.Detecting moving shadows:algorithms and evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918～923
[7]陈显华.智能视频监视系统中图像处理与识别技术研究：[硕士学位论文].青岛：中国海洋大学信号与信息处理,2004
[8]余理富.自然环境下图像序列运动目标检测关键技术研究：[硕士学位论文].湖南：国防科学技术大学电路与系统,2003
[9]Navneet Dalal, Bill Triggs.Histograms of oriented gradients for human detection.In:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1:886～893
[10]Coastal Syst.Station, Panama. An iterated-extended Kalman filter algorithm for tracking surface and sub-surface targets. MTS/IEEE,2002,3: 1283～1290
[11]Gordan N, Salmond D, Smith A.Novel approach to nonlinear/non-Gaussian Bayesian state estimation. Radar and Signal Processing,1993,140(2):107～113
[12]Cheng C, Rashid A, Ashfaq K. Multiple Object Tracking with Kernel Particle Filter. In:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1:566～573
[13]Dong-Gyu Sim,O-K Kwon, Rae-Hong Park. Object Matching Algorithms Using Robust Hausdorff Distance Measures, In:IEEE Transactions on Image Process,1999,8(2):425～429
[14]Haritaoglu I, Harwood D, Davis L. S. Real-time surveillance of people and their activities. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (8):809～830
[15]Wren C. R, Azarbayejani A, Darrell T, et al. Real-time tracking of the human body. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780～785
[16]Harville M, Gordon G, Woodfill J. Foreground segmentation using adaptive mixture models in color and depth. IEEE Workshop on Detection and Recognition of Events in Video,2001.3～11
[17]McKenna S. J, Jabri S, Duric A. Rosenfeld, et al. Tracking groups of people. Computer Vision and Image Understanding,2000,80:42～56
[18]Elgammal A, Duraiswami R, Harrwood D, et al. Background and foreground modeling using nonparametric Kernel density estimation for visual surveillance. In Proceedings of the IEEE,2002,90(7):1151～1163
[19]Akio Yoneyama, Chia H. Yeh, C.-C. Jay Kuo. Moving cast shadow elimination for robust vehicle extraction based on 2D joint vehicle/shadow models. In:IEEE Conference on Advanced Video and Signal Based Surveillance,2003.299～236
[20]Jiang C, Ward M.O. Shadow identification. In Proceedings of IEEE Computer Society Conference of Computer Vision,1992.606～612
[21]Sohail Nadimi,Bir Bhnu.Physical models for moving shadow and object detection in video. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1079～1087
[22]Leone A, Distante C, Buccolieri F.A texture-based approach for shadow detection. In:IEEE Conference on Advanced Video and Signal Based Surveillance,2005,371～376
[23]Wangt M, Chung Y.C, Chang C. L, et al. Shadow Detection and Removal for Traffic Images. In:IEEE International Conference on Networking, Sensing & Control,2004,1:649～655
[24]Jun-Wei Hsieh,Wen-Fong Hu,et al.Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image and Vision Computing,2003,21:505～516
[25]Bevilacqua A, Rofilli Robust. Denosing and moving shadows detection in traffic scenes. Computer vision and pattern Recogintion,2001.9～14
[26]Jacques JCS,Jung CR,Musse SR. Background Subtraction and Shadow Detection in Grayscale Video Sequences. Computer Graphics and Image Processing,2005.189～196
[27]Paragions N,Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects. In:Pattern Analysis and Machine,2000,22(3):266～280
[28]Bascle B, Deriche R. Region tracking through image sequences. Computer Vision,1995:302～307
[29]Jang D-S, Choi H-I. Active models for tracking moving objects. Pattern Recognition,2000,33(7):1135～1146
[30]Milan Sonka, Vaclav Hlavac, Roger Boyle著.图像处理、分析与机器视觉(第2版).(艾海舟,武勃等译).北京：人民邮电出版社,2003,387～391
[31]Barron J, Fleet D. Performance of optical flow techniques. International Journal of Computer Vision,1994,12(1):42～77
[32]Xu Li-Qun, Landabaso J. L, Pardas M. Shadow Removal with Blob-Based Morphological Reconstruction for Error Correction. IEEE ICASSP, 2005,4(5):729～732
[33]T. Hoprasert, D. Harwood, and L.S.Davis. A statistical approach for real-time robust background subtraction and shadow detection. In:Proceedings of the seventh IEEE International Conference on Computer Vision,1999.1～19
[34]Li-Qun Xu.An Efficient Object Segmentation Algorithm with Dynamic and Selective Background Updating and Shadow Removal. In:IEEE International Conference of Image Processing,2006.2393～2396
[35]Salvador E, Cavallaro A, Ebrahimi T.Cast shadow segmentation using invariant color features.Computer Vision and Image Understanding,2004,95(2):238～259
[36]Avidan S. Ensemble tracking. In:Proc IEEE Conf.on Computer Vision and Pattern Recognition, San Diego, CA,2005.494～501
[37]Porikli F. Achieving Real-Time Object Detection and Tracking Under Extreme Conditions. In:Journal of Real-time Image Processing,2006,1 (1): 33～40
[38]Tuzel O,Porikli F, Meer P.Region covariance:A fast descriptor for detection and classification. In proc ninth European Conference on computer vision, Graz, Austria,2006.589～600
[39]Porikli F, Tuzel 0, Meer P. Covariance Tracking using Model Update Based on Lie Algebra. In:IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2006.728～735
[40]Vincent Arsigny, Pierre Fillard, Xavier Pennec, et,al. Fast and Simple Calculus on Tensors in the Log-Euclidean Framework. Medical Image Computing and Computer-Assisted Intervention,2005(1):115～122
[41]http://www. intel. com/technology/computing/OpenCV/
[2]Robert T. Collins, Alan J. Lipton. Introduction to the special section on video surveillance. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):745～746
[3]王智灵,路婷婷,张硕奇.基于全局光流的多目标检测与跟踪.2008系统仿真技术及其应用学术会议,2008,10：265-268
[4]Stauffer C, Grimsonx C. Adaptive Background Mixture Models for Real-time Tracking. In:Proc IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado,1999,2:246～252
[5]Bai Sheng C,Yun Qi L.Indoor and outdoor people detection and shadow suppression by exploiting HSV color information. In:Proceedings of the Fourth International Conference on Computer and InformationTechnology. 2004.137～142
[6]Prati A, Mikic I,Trivedi M,et al.Detecting moving shadows:algorithms and evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918～923
[7]陈显华.智能视频监视系统中图像处理与识别技术研究：[硕士学位论文].青岛：中国海洋大学信号与信息处理,2004
[8]余理富.自然环境下图像序列运动目标检测关键技术研究：[硕士学位论文].湖南：国防科学技术大学电路与系统,2003
[9]Navneet Dalal, Bill Triggs.Histograms of oriented gradients for human detection.In:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1:886～893
[10]Coastal Syst.Station, Panama. An iterated-extended Kalman filter algorithm for tracking surface and sub-surface targets. MTS/IEEE,2002,3: 1283～1290
[11]Gordan N, Salmond D, Smith A.Novel approach to nonlinear/non-Gaussian Bayesian state estimation. Radar and Signal Processing,1993,140(2):107～113
[12]Cheng C, Rashid A, Ashfaq K. Multiple Object Tracking with Kernel Particle Filter. In:Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,1:566～573
[13]Dong-Gyu Sim,O-K Kwon, Rae-Hong Park. Object Matching Algorithms Using Robust Hausdorff Distance Measures, In:IEEE Transactions on Image Process,1999,8(2):425～429
[14]Haritaoglu I, Harwood D, Davis L. S. Real-time surveillance of people and their activities. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22 (8):809～830
[15]Wren C. R, Azarbayejani A, Darrell T, et al. Real-time tracking of the human body. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780～785
[16]Harville M, Gordon G, Woodfill J. Foreground segmentation using adaptive mixture models in color and depth. IEEE Workshop on Detection and Recognition of Events in Video,2001.3～11
[17]McKenna S. J, Jabri S, Duric A. Rosenfeld, et al. Tracking groups of people. Computer Vision and Image Understanding,2000,80:42～56
[18]Elgammal A, Duraiswami R, Harrwood D, et al. Background and foreground modeling using nonparametric Kernel density estimation for visual surveillance. In Proceedings of the IEEE,2002,90(7):1151～1163
[19]Akio Yoneyama, Chia H. Yeh, C.-C. Jay Kuo. Moving cast shadow elimination for robust vehicle extraction based on 2D joint vehicle/shadow models. In:IEEE Conference on Advanced Video and Signal Based Surveillance,2003.299～236
[20]Jiang C, Ward M.O. Shadow identification. In Proceedings of IEEE Computer Society Conference of Computer Vision,1992.606～612
[21]Sohail Nadimi,Bir Bhnu.Physical models for moving shadow and object detection in video. In:IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1079～1087
[22]Leone A, Distante C, Buccolieri F.A texture-based approach for shadow detection. In:IEEE Conference on Advanced Video and Signal Based Surveillance,2005,371～376
[23]Wangt M, Chung Y.C, Chang C. L, et al. Shadow Detection and Removal for Traffic Images. In:IEEE International Conference on Networking, Sensing & Control,2004,1:649～655
[24]Jun-Wei Hsieh,Wen-Fong Hu,et al.Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image and Vision Computing,2003,21:505～516
[25]Bevilacqua A, Rofilli Robust. Denosing and moving shadows detection in traffic scenes. Computer vision and pattern Recogintion,2001.9～14
[26]Jacques JCS,Jung CR,Musse SR. Background Subtraction and Shadow Detection in Grayscale Video Sequences. Computer Graphics and Image Processing,2005.189～196
[27]Paragions N,Deriche. Geodesic active contours and level sets for the detection and tracking of moving objects. In:Pattern Analysis and Machine,2000,22(3):266～280
[28]Bascle B, Deriche R. Region tracking through image sequences. Computer Vision,1995:302～307
[29]Jang D-S, Choi H-I. Active models for tracking moving objects. Pattern Recognition,2000,33(7):1135～1146
[30]Milan Sonka, Vaclav Hlavac, Roger Boyle著.图像处理、分析与机器视觉(第2版).(艾海舟,武勃等译).北京：人民邮电出版社,2003,387～391
[31]Barron J, Fleet D. Performance of optical flow techniques. International Journal of Computer Vision,1994,12(1):42～77
[32]Xu Li-Qun, Landabaso J. L, Pardas M. Shadow Removal with Blob-Based Morphological Reconstruction for Error Correction. IEEE ICASSP, 2005,4(5):729～732
[33]T. Hoprasert, D. Harwood, and L.S.Davis. A statistical approach for real-time robust background subtraction and shadow detection. In:Proceedings of the seventh IEEE International Conference on Computer Vision,1999.1～19
[34]Li-Qun Xu.An Efficient Object Segmentation Algorithm with Dynamic and Selective Background Updating and Shadow Removal. In:IEEE International Conference of Image Processing,2006.2393～2396
[35]Salvador E, Cavallaro A, Ebrahimi T.Cast shadow segmentation using invariant color features.Computer Vision and Image Understanding,2004,95(2):238～259
[36]Avidan S. Ensemble tracking. In:Proc IEEE Conf.on Computer Vision and Pattern Recognition, San Diego, CA,2005.494～501
[37]Porikli F. Achieving Real-Time Object Detection and Tracking Under Extreme Conditions. In:Journal of Real-time Image Processing,2006,1 (1): 33～40
[38]Tuzel O,Porikli F, Meer P.Region covariance:A fast descriptor for detection and classification. In proc ninth European Conference on computer vision, Graz, Austria,2006.589～600
[39]Porikli F, Tuzel 0, Meer P. Covariance Tracking using Model Update Based on Lie Algebra. In:IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2006.728～735
[40]Vincent Arsigny, Pierre Fillard, Xavier Pennec, et,al. Fast and Simple Calculus on Tensors in the Log-Euclidean Framework. Medical Image Computing and Computer-Assisted Intervention,2005(1):115～122
[41]http://www. intel. com/technology/computing/OpenCV/