摘要
运动车辆的有效检测和准确跟踪是现代智能交通系统研究的核心部分。基于视觉的车辆识别由于其良好的适应性和性价比,受到了广泛的关注,是近年来图像处理和人工智能等应用领域的研究热点。该识别算法的主要手段是通过外观特征识别候选目标。然而由于现实环境中复杂的噪声的存在,特定特征的存在、量化和解释往往是模糊的,因此,当前的算法在面临同时提高准确度和敏感度的两难要求时遇到了概念和计算上的双重困难。本文给出了车辆识别问题的数学模型,并提出了一种基于概率模型的动态特征选择方法。通过构建特征有向图的方式,充分的考虑到了真实世界中不同特征对识别结果作用的不平衡性,以及特征之间的相互依赖关系等诸多因素,使得整个识别过程更符合车辆识别是多特征共同匹配、综合作用这一客观规律,是对人类辨别事物过程的一个更近似和更有效的模拟。最后通过与原有后方车辆识别算法的对比实验,从实验结果的ROC曲线可以看出,不仅在多种闽值下提高了识别率,而且准确度也由原来的0.9286提高到了0.9513,进一步证实了该方法是一种可同时提高识别准确度和敏感度,并且有助于解决特征竞争等问题的有效方法。
Effective and accurate detection and tracking of moving vehicles in video sequences is the key to modern intelligent traffic monitoring systems. Vision based vehicle recognition has received extensive attentions because of its fine applicability and high cost-performance ratio. Thus, vision based vehicle recognition has become a popular research topic in the field of image processing and artificial intelligence. The recognition algorithm mainly implements the synthesis which uses both appearance based and knowledge based features to identify its candidates. However, due to the unpredicted complex noises in real world environments, existences, quantifications and explanations for certain features are often ambiguous, which makes current algorithm hard to fulfill the dilemmatic high sensitivity/accuracy restriction, and an improvement for a certain feature (or data sets) often leads to degeneration for others. This dissertation provides a mathematical model for vehicle recognition, and proposes a probability model based feature selection method which enables the dynamic feature selection and multigrain feature evaluations. The method of feature digraph construction takes very sufficient thought of the fact that, in the real world, the imbalance that different features result in different outcomes of recognitions; and the inter-dependencies and the inter-relationships among different features, etc. By doing so it makes the entire recognition process converge to the objective laws that vehicle recognitions is of multi-feature matching and collaboration. It is the more accurate and more effective imitation of the process of human-recognitions. Eventually, by comparing with the former rear vehicle recognition algorithms in experiments, ROC curves show that not only the recognition rate was improved in a variety of thresholds, but also the accuracy was raised from 0.9286 to 0.9513, it further proves that the method (mentioned above) is an effective solution which can increase the accuracy and sensitivity of recognitions, and it is very helpful in solving feature-racing alike problems.
引文
1.王征平,邵迈,蔡少渠.智能运输系统的产生与发展[J],智能交通,2003：48-50.
2.孙晋文.智能运输系统与汽车的智能化技术[J],汽车研究与开发,2000：15-16.
3. Margrit Betke, Esin Haritaoglu, Larry S. Davis. Real-time multiple vehicle detection and tracking from a moving vehicle[J], Machine Vision and Applications,2000,12:69-83.
4. Juan Carlos Rojas, Jill D. Crisman. VEHICLE DETECTION IN COLOR IMAGES[J], Northeastern University Boston, Massachussets, U.S.A.0-7803-4269-0/97 IEEE, 1998:2-8.
5. C. Knoeppel, A. S chanz B.Michaeli.s, Robust Vehicle Detection at Large Distance Using Low Resolution Cameras[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5.
6. M. Bertozzi, A.Broggi, A. Fascioli'S. Nichele. Stereo Vision-based Vehicle Detection[J], Proceedings of the IEEE Intelligent Vehicles Symposium 2000 Dearborn (MI), USA October,2000:3-5.
7. Massimo Bertozzi, AlbertO Broggi, Gianni Conte. Alessandra Fasciolj obstacle and lane detection on Argo[J], Department of Information University of Parma, Parma, Italy.
8. J. M. Collado, C. Hilario A. de la Escalera J. M Armingol. Model Based Vehicle Detection for Intelligent Vehicles[J],2004 IEEE Intelligent Vehicles Symposium University of Parma Parma, Italy,2004:14-17.
9.施树明,储江伟,李斌,郭烈,王荣本.基于单目视觉的前方车辆探测方法[J],农业机械学报,35(4)：12-23.
10. Z. Sun, R. Miller, G. Bebis, D. DiMeo. A real-time precrash vehicle detection system[J], Proceedings of the Sixth IEEE Workshop on Applications of Computer Vision (WACV'02),2002:101-106.
11.张辉,王强,徐光佑等.运动目标的快速检测、跟踪和判别[J],清华大学学报(自然科学版),2002,42(10)：1401-1404.
12. J. Wu, X. Zhang, J. Zhou. Vehicle detection in static road images with PCA-and-Wavelet-based classifier[C], IEEE Intelligent Transportation Systems Conference Proceedings, Oakland, USA,2001.740-744.
13. T. Kato, Y. Ninomiya, I. Masaki. Preceding vehicle recognition based on learning from sample images[J], IEEE Trans. on Intelligent Transportation Systems,2002,3(4):252-260.
14. M. Bertozzi, A. Broggi. GOLD:A parallel real-time stereo vision system for generic obstacle and lane detcction[J], IEEE Trans. on Image Processing,1998,7(1):62-81.
15. D. Guo, T. Fraichard, M. Xie, and C. Laugier. Color modeling by spherical influence field in sensing driving environment[C], IEEE Intelligent Vehicle Symposium,2000.249-254.
16. E. Dickmanns, et. al., The seeing passenger car'vamorse'[C], International Symposium on Intelligent Vehicles,1994.24-26.
17. M. Bertozzi, A. Broggi, and S. Castelluccio, A real-time oriented system for vehicle detection[J], Journal of Systems Architecture,1997:317-325.
18. N. Matthews, P. An, D. Charnley, and C. Harris, Vehicle detection and recognition in greyscale imagery, Control Engineering Practice,1996,4:473-479.
19. C. Tzomakas and W. Seelen, Vehicle detection in traffic scenes using shadows[C], Tech. Rep.98-06, Institut fur neuroinformatik, Ruht-universitat, Bochum, Germany,1998, 213-221.
20. U. Handmann, T. Kalinke, C. Tzomakas, M. Werner, and W. Seelen, An image processing system for driver assistance[J],2000,18(5):13-15.
21. P. Parodi and G. Piccioli, A feature-based recognition scheme for traffic scenes[C], IEEE Intelligent Vehicles Symposium,1995.229-234.
22. T. Kato, Y. Ninomiya, I. Masaki. Preceding vehicle recognition based on learning from sample images [J], IEEE Transaction on Intelligent Transportation Systems,2002,3(4): 252-260
23. T. Bucher, C. Curio et al., Image processing and behavior planning for intelligent vehicles[J], IEEE Transactions on Industrial Electronics,2003,50(1):62-75.
24. Marie-Pierre Dubuisson, Anil K. Jain, and William C. Taylor. A vision-based vehicle matching system[C]. In Intelligent Vehicles Symposium,1994.266-271.
25. R. Cucchiara, M. Piccardi, Vehicle detection under day and night illumination[C], International ICSC Symposium on Intelligent Industrial Automation,1999.75-82
26. G. Zhao and S. Yuta, Obstacle detection by vision system for autonomous vehicle[J], Intelligent Vehicles,1993:31-36.
27. M.Suwa, Y. Wu, M. Kobayashi et al., A stereo-based vehicle detection method under windy conditions[C], IEEE Intelligent vehicle symposium,2000.246-249.
28. A. Broggi, M. Bertozzi and A. Fascioli, Self-calibration of a stereo-vision system for automotive applications[C], IEEE Intl. Conf. on Robotics and Automation,2001.183-191
29. B. Heisele. W. Bitter. Obstacle detection based on color blob flow[C], IEEE intelligent Vehicles Symposium,1995.282-286.
30.腾力里.一个基于VIDEO的DAS原型系统的设计与实现[D],沈阳东北大学硕士学位论文,2007
31.王影.基于边缘的车道线识别算法的研究与实现[D],沈阳东北大学硕士学位论文,2008
32. A. Bensrhair, M. Bertozzi, A. Broggi, P. Miche, S. Mousset and G. Toulminet, A Cooperative Approach to Vision-based Vehicle Detection[C], IEEE Conference on Intelligent Transportation System,2001.213-217.
33. M. Betke, E. Haritaoglu and L. Davis, Multiple Vehicle Detection and Tracking in Hard Real Time[C], IEEE Symposium in Intelligent Vehicles,1996.341-346.
34. A.Broggi and P. Cerri, Multi-Resolution Vehicle Detection Using Artifical Vision[C], IEEE Intelligent Vehicle Symposium,2004.132-136
35. N. Matthew, P.An, D.Charnley and C.Harris, Vehicle Detection and Recognition in Grayscale Imagery[C], Control Engineering Practice,1996.413-415
36. D. Magee, Tracking multiple vehicles using foreground, background and motion models, Image Vis. Comput. Vol.22 pp.143-155,2004.
37. Robert T. Collins, Alan J. Lipton, Hironobu Fujiyoshi, Takeo Kanade. Algorithms for cooperative multi-sensor surveillance [J], Proceedings of the IEEE,2001,89(10): 1456-1477.
38. C. Goerick, D. Noll and M. Werner, "Artificial Neural Networks in Real time Car Detection and Tracking Applications", Pattern Recognition Letters, vol.17,996.
39. T. Kato, Y. Ninomiya and I. Masaki, "Preceding Vechile Recognition Based on Learning From Sample Images", IEEE Trans. Intelligent Transportation System. Vol.3 no.4 2002.
40. C. Papageorgiou and T. poggio, "A Trainable System for Object Detection", International Journal of Computer Vision, vol.38, no.1,2000.
41 Wei Liu, Xuezhi Wen, Bobo Duan, Huai Yuan and Nan Wang, Rear Vehicle Detection and Tracking for Lane Change Assist[C], IEEE Intelligent Vehicles Symposium, 2007.123-127.
42. Roya Rad and Mansour Jamzad, "Real time classification and tracking of multiple vehicles in highways", Pattern Recognition Letters, Vol.26, Issue 10,2005
43. Y. Zhu, D. Comaniciu, V. Ramesh, M. Pellkofer and T. Koehler, An integrated framework of vision based vehicle detection with knowledge fusion[C], IEEE Intelligent Vehicles Symposium,2005:101-124.
44. N. Kawasaki, U. Kiencke, Standard platform for sensor fusion on advanced driver assistance system using Bayesian Network[C], IEEE Intelligent Vehicles Symposium, 2004.141-146.
45. George Fung, Nelson Yung, and Grantham Pang. Vehicle shape approximation from motion for visual traffic surveillance[J]. In Proc. IEEE Conf. Intelligent Transport System, 2001:608-613.
46. Marie-Pierre Dubuisson, Anil K. Jain, and William C. Taylor. A vision-based vehicle matching system[C]. In Intelligent Vehicles Symposium,1994:266-271.
47. T. Ito, K. Yamada and K. Nishioka, Understanding driving situations using a network model. Intelligent vehicles,1995:48-53.
48. U. Regensburger and V. Graefe. Visual recognition of obstacles on roads. Intelligent Robots and Systems (V. Graefe, ed.), Academic Press, Inc.,1995:73-86.
49. A. Bensrhair, M. Bertozzi, A. Broggi, P. Miche, S. Mousset and G. Moulminet. A cooperative approach to vision-based vehicle detection[C]. IEEE Intelligent Transportation Systems,2001.209-214.
50. N. Matthews, P. An, D. Charnley, C. Harris. Vehicle detection and recognition in grey scale imagery. Control Engineering Practice,1996,4:473-479.
51. C. Goerick, N. Detlev, M. Werner. Artificial neural networks in real-time car detection and tracking applications. Pattern Recognition Letters,1996,17:335-343.
52. Z. Sun, G. Bebis, R. Miller. Quantized wavelet features and support vector machines for on-road vehicle detection. The Seventh International Conference on Control. Automation, Robotics and Vision, Singapore,2002:454-460.
53.孙即样,王晓华,钟山等.模式识别中对的特征提取与计算机视觉不变量[M].北京：国防工业出版,2001.
54. Olivier Chapelle, et al. SVMs for Histogram-Based Image Classification[J]. IEEE Trans. On Neural Networks,1999,10(5):1055-1064.
55. Pontil M, Verri A. Support Vector Machines for 3D Object Recognition[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence,1998,20(6):637-646.
56. P. Kaizinga, N. Petkov, Grigorescu. Comparison of texture features based on gabor filters[C]. Proceedings of the 10th International Conference on Image Analysis and Processing,1999.142-147.
57.鲍晓东,张仙妮.智能交通系统的现状及发展[J],道路交通与安全,2006,8：15-18.
58. Chapelle, O., Vapnik, V., et al. Choosing Multiple Parameters for Support Vector Machines. Machine Learning,2002,46:131-160.
59. Massimo Bertozzi, Albert Broggi, Gianni Conte, Alessandra Fasciolj. Obstacle and lane detection on Argo [C], In Proceedings of IEEE Conference on Intelligent Transportation System (ITSC 97),1997.1010-1015.
60. Zengjia Yan, Hao Zhang, Huadong Meng, Xiqin Wang. Cast Vehicle Shadow Segmentation based on Contour Analysis[C]. In Proceedings of IEEE Conference on Intelligent Transportation Systems.2007.
61. Chunyang, Bobo Duan, Wei Liu, Jinwei Zhang. A Dynamic Feature Selection Method for Vision based Vehicle Recognition[C]. World Congress on Computer Science and Information Engineering, Los Angles, US.2009.
62. Chen Y, Lin C. Combining SVMs with Various Feature Selection Strategies [EB/OJ], http://www.csie.ntu.edu.tw/-cjlin/papers/features.pdf.2005.
63. Deaho Lee, Youngtae Park. Robust vehicle detection based on shadow classification [C], In Proceedings of 18th International Conference on Pattern Recognition (ICPR 2006), 2006,1167-1170.