基于混合高斯模型和粒子滤波理论的视频车辆跟踪算法
|
摘要
车辆跟踪是智能交通系统(ITS,Intelligent Transportation System)中的重要技术,而其中基于视频检测的车辆轨迹跟踪技术由于信息量大、可用范围广,成为许多国家的研究热点。
本课题研究的目的在于针对ITS领域中的关键技术,研究基于视频的运动车辆轨迹获取的相关问题。为实现视频的自动检测交通流和交通事件等提供算法前提。
本文详细分析了运动车辆轨迹获取中较为常用的方法,根据实验和分析,得到了适合实际应用的视频车辆跟踪算法,本文主要的研究内容包括以下几个方面:
(1)根据算法调试、对比及实际应用的要求,使用C++编程语言设计程序,并在Windows系统上设计算法可视化调试平台,然后将程序移植到Linux系统实现调试应用。
(2)使用简单的模板匹配算法和图像的仿射变换算法对抖动的视频进行防抖处理,以输出稳定的图像。
(3)采用以高斯混合背景模型理论为基础的运动车辆检测算法,实现视频中运动车辆检测,为算法后续操作提供基础信息,通过程序实现将该方法与其它常用方法进行比较分析。
(4)使用以光流法为基础结合图像金字塔操作的特征点跟踪模块,该模块能够得到精确的车辆位置变化信息,设计程序实现该算法模块功能,完成轨迹精确位置的获取。
(5)利用粒子滤波算法得到车辆运动趋势信息的预测,将该算法与以图像特征为基础的模板匹配算法进行比较分析,评价算法的可行性,增强算法的鲁棒性。
本文中基于混合高斯模型的运动车辆检测算法具有较强的适应性,结合粒子滤波的预测功能在提高整个算法鲁棒性的同时,使用特征的跟踪算法为车辆轨迹增加了更为丰富的信息。由于算法整体性能的提高,使其成为实际检测应用中可靠的依据。
As an important part of the ITS, the vehicle tracking and the obtaining of the vehicle trajectory become a research focus in the world. According to the key techniques of ITS, some problems related to the moving vehicle trajectory obtaining are researched.
In this thesis, several useful methods for vehicle trajectory obtaining are analyzed. Compared with them, the most powerful algorithm is adopted. Then the program system that is up to par of application is designed based on the algorithm.
According to the needs of the algorithm debuging, comparing and application, the program on both windows and linux operating systems based on the information of vehicles is designed with C++ program language.
In case of the video’s shaking, the template matching is used to estimate the movement’s matrix. The affine algorithm is used to reshape the image to reduce the shaking.
Gaussian model theory is used to detect moving vehicles. Then information of vehicles is prepared for next processes of the algorithm. The effect of mixture Gaussian model theory is also compared with other algorithms.
In order to improve the stability of the algorithm, Condensation filter is used to estimate the information of moving vehicles. This information then is provided to improve the trajectory matching and updating.
Both optical flow method and the pyramid processing are adopted to track features of vehicles. From this step, accurate positions of moving vehicles are obtained.
Using the algorithms such as Gaussian model theory, Condensation filter and features tracking correctly, and combining them properly, creditable trajectories are obtained and used in practical surveillance system.
本课题研究的目的在于针对ITS领域中的关键技术,研究基于视频的运动车辆轨迹获取的相关问题。为实现视频的自动检测交通流和交通事件等提供算法前提。
本文详细分析了运动车辆轨迹获取中较为常用的方法,根据实验和分析,得到了适合实际应用的视频车辆跟踪算法,本文主要的研究内容包括以下几个方面:
(1)根据算法调试、对比及实际应用的要求,使用C++编程语言设计程序,并在Windows系统上设计算法可视化调试平台,然后将程序移植到Linux系统实现调试应用。
(2)使用简单的模板匹配算法和图像的仿射变换算法对抖动的视频进行防抖处理,以输出稳定的图像。
(3)采用以高斯混合背景模型理论为基础的运动车辆检测算法,实现视频中运动车辆检测,为算法后续操作提供基础信息,通过程序实现将该方法与其它常用方法进行比较分析。
(4)使用以光流法为基础结合图像金字塔操作的特征点跟踪模块,该模块能够得到精确的车辆位置变化信息,设计程序实现该算法模块功能,完成轨迹精确位置的获取。
(5)利用粒子滤波算法得到车辆运动趋势信息的预测,将该算法与以图像特征为基础的模板匹配算法进行比较分析,评价算法的可行性,增强算法的鲁棒性。
本文中基于混合高斯模型的运动车辆检测算法具有较强的适应性,结合粒子滤波的预测功能在提高整个算法鲁棒性的同时,使用特征的跟踪算法为车辆轨迹增加了更为丰富的信息。由于算法整体性能的提高,使其成为实际检测应用中可靠的依据。
As an important part of the ITS, the vehicle tracking and the obtaining of the vehicle trajectory become a research focus in the world. According to the key techniques of ITS, some problems related to the moving vehicle trajectory obtaining are researched.
In this thesis, several useful methods for vehicle trajectory obtaining are analyzed. Compared with them, the most powerful algorithm is adopted. Then the program system that is up to par of application is designed based on the algorithm.
According to the needs of the algorithm debuging, comparing and application, the program on both windows and linux operating systems based on the information of vehicles is designed with C++ program language.
In case of the video’s shaking, the template matching is used to estimate the movement’s matrix. The affine algorithm is used to reshape the image to reduce the shaking.
Gaussian model theory is used to detect moving vehicles. Then information of vehicles is prepared for next processes of the algorithm. The effect of mixture Gaussian model theory is also compared with other algorithms.
In order to improve the stability of the algorithm, Condensation filter is used to estimate the information of moving vehicles. This information then is provided to improve the trajectory matching and updating.
Both optical flow method and the pyramid processing are adopted to track features of vehicles. From this step, accurate positions of moving vehicles are obtained.
Using the algorithms such as Gaussian model theory, Condensation filter and features tracking correctly, and combining them properly, creditable trajectories are obtained and used in practical surveillance system.
引文
1刘允才,张素,施鹏飞.智能交通国际发展概况和国内优先考虑的课题.公路. 2001,11:31~36
2宋颖华.交通检测技术及其发展.公路. 2000,(9):39~42
3史其信,郑为中.智能交通系统(ITS)共用信息平台框架及解决方案初步分析.交通运输工程与信息学报. 2003, (1):41~49
4 I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machhine Intelligence. 2000, 22(8):809~830
5史其信,陆化普.智能交通系统的相关技术及研究发展策略.中国土木工程学会第八届年会论文集,清华大学出版社. 1998, (1):135~141
6郁梅,蒋刚毅,郁伯康.智能交通系统中的计算机视觉技术应用.计算机技术与应用. 2001,(1):37~43
7 E. Stringa. Morphological change detection algorithms for surveillance applications. Pro British Machine Vision Conference, Bristol, UK. 2000: 402~411
8 J. M. Roberts. Attentive visual tracking and trajectory estimation for dynamic scene segmentation. University of Southampton Ph.D. thesis. 1994:23~36
9 B. Coifman, D. Beymer, J. Malik. A real-time computer vision system for vehicle tracking and traffic surveillance. Transport. Res:Part C. 1998, 6(4):271~288
10 C. Sechell. Applications of computer vision to road-traffic monitoring, University of Bristol, Department of Computer Science, Ph.D. thesis. 1997:17~30
11 S. Kamijo, M. Sakauchi. Illumination invariant and occlusion robust vehicle tracking by sptio-temporal MRF model. Pro. 9th World Congress on ITS. Chicago. 2002:1~9
12 D. Magee. Tracking multiple vehicles using foreground background and models. Image Vis. Comput.2004, 22(2):143~155
13章毓晋.图像工程(上册)—图像处理和分析.第一版.清华大学出版社,1999:17~20
14 K. Sage, S. Young. Computer vision for security applications. 32nd Annual 1998 International Camahan Conference on Security Technology of Proceeding. 1998, (11):210～215
15李玲玲.基于数学形态学的灰度线形态识别研究与发展.计算机工程与应用. 2001,11:104~105
16 T. Zhao, R. Nevatia. Tracking multiple humans in crowded environment. CVPR’04. Vol II: 406~413
17 S. Masound, O. Martin, R. F. Ketal. Detection and classification for vehicles[J], IEEE Transactions on Intelligent Transportation Systems. 2002, 3(1):36~47
18 J. Chamorro-Martinez, J. Fernandez-Valdivia. A New Approach to Motion Pattern Recongnition and Its Application to Optical Flow Estimation. IEEE Transactions on Systems, Man, and Cybernetics-Part C: Application and Reviews. 2007, 37(1): 39~51
19 T. Meier, K. N. Ngun. Video Segmentation for Content-Based Coding[J]. IEEE Trans. On Circuits and Systems for Video Technology. 1999, 9(8):1190~1203
20 A. W. Gruen. Adaptive least squares correlation: A powerful image matching technique. Jornal of Photogrammetry, Remote Sensing and Cartography. 1985, 14(3):175~187
21 D. Douglas, M. Dimitris. Optical flow constraints on deformable models with applications to face tracking. International journal of computer vision. 2000, 38(2):99~127
22 C. Wren, A. Azarbayejani, T. Darrell, A. Pentland. Pfinder: Real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19(7):780~785
23 C. Stauffer, WEL. Grimson. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2000, 22(8): 747~57
24 S. Huwer, H. Niemann. Adaptive Change Detection for Real-time Surveillance Applications. In Proceedings of the 3rd IEEE International Workshop on Visual Surveillance, Dublin, Ireland. 2000, 7:36~45
25 L. Li, W. M. Huang, I. Y. Gu, Q. Tian. Foreground object detection in changing background based on color co-occurrence statistics. In Proceedings IEEE Workshop on Application of Computer Vision. 2002:202~205
26 S. H. Kim, H. R. Tizhoosh, M. Kamel. Choquet integral-based aggregation of image template matching algorithms, 22th International Conference of the North American Fuzzy Information Processing Society, no.24-26. 2003: 143~148
27 J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques. International Journal of Computer Vision. 1994, 12(1):42~77
28 K. Toyama, J. Krumm, B. Brumitt, B. Meyers. Principles and practice of background maintenance. Proceedings of IEEE International Conference on Computer Vision. 1999, (7):255～261
29 H. W. Sorenson. Least Squares Estimation: from Gauss to Kalman. IEEE Spectrum. 1970(7):63~68
30 D. Metaxa. Facial Features Tracking for Gross Head Movement analysis and Expression Recognition. IEEE Multimedia Signal Processing, 2007. MMSP 2007. IEEE 9th Workshop on 1-3 Oct. 2007:2
31 A. Baumberg. Reliable feature matching across widely separated views [A]. In: International Conference on Computer Vision and Pattern Recognition [C]. Hilton Head Island, SC, USA. 2000:774~781
32 J. Shi, C. Tomasi. Good Features to Track. 1994 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'94). 1994: 593~600
33 B. D. Lucas, T. Kanade. An iterative image registration technique with an application to stereo vision. IJCAI. 1981:13~14
34江志军,易华蓉.一种基于图像金字塔光流的特征跟踪方法.武汉大学学报,信息科学版. 2007, 32(8):680~683
35杨文杰,胡明昊,杨靖宇.一种基于光流的障碍物估计计算.计算机工程与应用, 2006, (5):80~81
36 C. Harris, M. Stephens. A combined corner and edge detector. In Alvey88.1988: 147~152
37 R.E. Kalman. A new Approach to Linear Filtering and Prediction Problems [J]. Transactions of the ASME-Journal of Basic Engineering. 1960, 82(Series D):35~45
38 J. Versavel. Road Safety through Video Detection [C]. The Proceeding of the IEEE International Conference on Intelligent Transportation Systems. 1999:753~757
39温军燕,黄洪琼,杨成.视频检测技术在城市隧道中的应用.中国市政工程. 2006, 8(4):64~65
40杨昌勇,刘建伟,曹泉.车辆违章逆行的图像自动检测与识别.计算机工程与设计. 2005, 26(10):2825~2827
2宋颖华.交通检测技术及其发展.公路. 2000,(9):39~42
3史其信,郑为中.智能交通系统(ITS)共用信息平台框架及解决方案初步分析.交通运输工程与信息学报. 2003, (1):41~49
4 I. Haritaoglu, D. Harwood, L. S. Davis. W4: Real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machhine Intelligence. 2000, 22(8):809~830
5史其信,陆化普.智能交通系统的相关技术及研究发展策略.中国土木工程学会第八届年会论文集,清华大学出版社. 1998, (1):135~141
6郁梅,蒋刚毅,郁伯康.智能交通系统中的计算机视觉技术应用.计算机技术与应用. 2001,(1):37~43
7 E. Stringa. Morphological change detection algorithms for surveillance applications. Pro British Machine Vision Conference, Bristol, UK. 2000: 402~411
8 J. M. Roberts. Attentive visual tracking and trajectory estimation for dynamic scene segmentation. University of Southampton Ph.D. thesis. 1994:23~36
9 B. Coifman, D. Beymer, J. Malik. A real-time computer vision system for vehicle tracking and traffic surveillance. Transport. Res:Part C. 1998, 6(4):271~288
10 C. Sechell. Applications of computer vision to road-traffic monitoring, University of Bristol, Department of Computer Science, Ph.D. thesis. 1997:17~30
11 S. Kamijo, M. Sakauchi. Illumination invariant and occlusion robust vehicle tracking by sptio-temporal MRF model. Pro. 9th World Congress on ITS. Chicago. 2002:1~9
12 D. Magee. Tracking multiple vehicles using foreground background and models. Image Vis. Comput.2004, 22(2):143~155
13章毓晋.图像工程(上册)—图像处理和分析.第一版.清华大学出版社,1999:17~20
14 K. Sage, S. Young. Computer vision for security applications. 32nd Annual 1998 International Camahan Conference on Security Technology of Proceeding. 1998, (11):210～215
15李玲玲.基于数学形态学的灰度线形态识别研究与发展.计算机工程与应用. 2001,11:104~105
16 T. Zhao, R. Nevatia. Tracking multiple humans in crowded environment. CVPR’04. Vol II: 406~413
17 S. Masound, O. Martin, R. F. Ketal. Detection and classification for vehicles[J], IEEE Transactions on Intelligent Transportation Systems. 2002, 3(1):36~47
18 J. Chamorro-Martinez, J. Fernandez-Valdivia. A New Approach to Motion Pattern Recongnition and Its Application to Optical Flow Estimation. IEEE Transactions on Systems, Man, and Cybernetics-Part C: Application and Reviews. 2007, 37(1): 39~51
19 T. Meier, K. N. Ngun. Video Segmentation for Content-Based Coding[J]. IEEE Trans. On Circuits and Systems for Video Technology. 1999, 9(8):1190~1203
20 A. W. Gruen. Adaptive least squares correlation: A powerful image matching technique. Jornal of Photogrammetry, Remote Sensing and Cartography. 1985, 14(3):175~187
21 D. Douglas, M. Dimitris. Optical flow constraints on deformable models with applications to face tracking. International journal of computer vision. 2000, 38(2):99~127
22 C. Wren, A. Azarbayejani, T. Darrell, A. Pentland. Pfinder: Real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997, 19(7):780~785
23 C. Stauffer, WEL. Grimson. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2000, 22(8): 747~57
24 S. Huwer, H. Niemann. Adaptive Change Detection for Real-time Surveillance Applications. In Proceedings of the 3rd IEEE International Workshop on Visual Surveillance, Dublin, Ireland. 2000, 7:36~45
25 L. Li, W. M. Huang, I. Y. Gu, Q. Tian. Foreground object detection in changing background based on color co-occurrence statistics. In Proceedings IEEE Workshop on Application of Computer Vision. 2002:202~205
26 S. H. Kim, H. R. Tizhoosh, M. Kamel. Choquet integral-based aggregation of image template matching algorithms, 22th International Conference of the North American Fuzzy Information Processing Society, no.24-26. 2003: 143~148
27 J. Barron, D. Fleet, S. Beauchemin. Performance of optical flow techniques. International Journal of Computer Vision. 1994, 12(1):42~77
28 K. Toyama, J. Krumm, B. Brumitt, B. Meyers. Principles and practice of background maintenance. Proceedings of IEEE International Conference on Computer Vision. 1999, (7):255～261
29 H. W. Sorenson. Least Squares Estimation: from Gauss to Kalman. IEEE Spectrum. 1970(7):63~68
30 D. Metaxa. Facial Features Tracking for Gross Head Movement analysis and Expression Recognition. IEEE Multimedia Signal Processing, 2007. MMSP 2007. IEEE 9th Workshop on 1-3 Oct. 2007:2
31 A. Baumberg. Reliable feature matching across widely separated views [A]. In: International Conference on Computer Vision and Pattern Recognition [C]. Hilton Head Island, SC, USA. 2000:774~781
32 J. Shi, C. Tomasi. Good Features to Track. 1994 IEEE Conference on Computer Vision and Pattern Recognition (CVPR'94). 1994: 593~600
33 B. D. Lucas, T. Kanade. An iterative image registration technique with an application to stereo vision. IJCAI. 1981:13~14
34江志军,易华蓉.一种基于图像金字塔光流的特征跟踪方法.武汉大学学报,信息科学版. 2007, 32(8):680~683
35杨文杰,胡明昊,杨靖宇.一种基于光流的障碍物估计计算.计算机工程与应用, 2006, (5):80~81
36 C. Harris, M. Stephens. A combined corner and edge detector. In Alvey88.1988: 147~152
37 R.E. Kalman. A new Approach to Linear Filtering and Prediction Problems [J]. Transactions of the ASME-Journal of Basic Engineering. 1960, 82(Series D):35~45
38 J. Versavel. Road Safety through Video Detection [C]. The Proceeding of the IEEE International Conference on Intelligent Transportation Systems. 1999:753~757
39温军燕,黄洪琼,杨成.视频检测技术在城市隧道中的应用.中国市政工程. 2006, 8(4):64~65
40杨昌勇,刘建伟,曹泉.车辆违章逆行的图像自动检测与识别.计算机工程与设计. 2005, 26(10):2825~2827