路面车辆实时检测与跟踪的视觉方法

沈峘; 李舜酩; 柏方超; 缪小冬; 李芳培

doi:doi:10.3788/aos20103004.1076

光学学报, 2010, 30 (4): 1076, 网络出版: 2010-04-20

路面车辆实时检测与跟踪的视觉方法

On Road Vehicles Real-Time Detection and Tracking Using Vision Based Approach

论文大纲

沈峘 ^*李舜酩柏方超缪小冬李芳培

作者单位

南京航空航天大学能源与动力学院,江苏南京 210016

机器视觉车辆检测目标跟踪智能车辆智能交通系统 machine vision vehicle detection object tracking intelligent vehicles intelligent traffic system

摘要

为向驾驶者提供有效的车辆位置信息,提高驾驶安全性,提出了一种融合多种目标特征的单目视觉车辆检测与跟踪方法。首先,利用车辆尾部的结构对称性提取出感兴趣区域,减少搜索范围。再利用车辆底部的阴影特征,在感兴趣区域中搜寻车辆可能出现的位置,找出假设目标。然后,利用亮度和轮廓信息对假设目标进行对称性验证,排除虚假目标。同时,融合颜色和梯度方向建立目标特征模型,利用均值平移算法在随后的图像序列中对目标进行快速跟踪定位。检测与跟踪联合工作在一种互动机制下,大幅改善了算法的有效性和实时性。实验结果显示,提出方法的正确识别率为96.34％,平均处理速度达24.27 frame/s,能够满足车辆驾驶安全性和实时性要求。

Abstract

A novel monocular camera based on road vehicle detection and trcking approach by fuse multi-cues of object is present to improve drive security by providing some effective on road vehicles position information for driver. First,the horizontal symmtery of vehicle rear view is utilized to achieve the region of interest (ROI) extract so as to reduce search area of following process. And then,the sign of underneath shadow is employed to generate hypothetical positions on which potantial vehicles maybe present. Following,both image intensity and figure information are combined to used to verify the vertical symmetry of the potential vehicle candidates. Meanwhile,mean shift procedure,based on the object feature model of combine color histogram and orientation histogram,is employ to fast search the potantial objects between two sequential image frames. More improtant,both detection and tracking cooperate work under a interactive mechanism which can dramatically improve both detection efficiency and real-time. Experimental results show that the propsed apporach can achieve 96.34% correct recognition rate and run on an average 24.27 frame/s,which validate the vehicle drive security and real-time requirements.

参考文献

[1] . 智能车辆发展及其关键技术研究现状[J]. 传感器与微系统, 2009, 1(4): 1-4.

. . Survey of intelligent vehicles development and its key supporting technologies[J]. Transducer and Microsystem Technologies, 2009, 28(1): 1-4.

[2] . Bertozzi,A. Broggi,A. Fascioli. Vision-based intelligent vehicles:State of the art and perspectives[J]. Robotics and Autonomous Systems, 2000, 32(1): 1-16.

[3] 管志强,陈钱,顾国华等. 基于光流直方图的云背景下低帧频小目标探测方法[J]. 光学学报,2008,28(8):1496-1501

Guan Zhiqiang,Chen Qian,Gu Guohua et al.. Dim target detection based on optical flow histgram in low frame frequence in clouds background[J]. Acta Optica Sinica,2008,28(8):1496-1501

[4] 田玉敏,万波,董文涛. MPEG-4视频中运动背景下的目标检测算法[J]. 光学学报,2009,29(5):1227-1231

Tian Yumin,Wan Bo,Dong Wentao. Object detection algorithm based on moving background in MPEG-4 video[J]. Acta Optica Sinica,2009,29(5):1227-1231

[5] 管志强,陈钱,钱惟贤等. 一种基于算法融合的红外目标跟踪方法[J]. 光学学报,2008,28(5):860-865

Guan Zhiqiang,Chen Qian,Qian Weixian et al.. Infrared target tracking algorithm based on algorithm fusion [J]. Acta Optica Sinica,2008,28(5):860-865

[6] . Bertozzi,A Broggi. Gold:A parallel real-time stereo vision system for generic obstacle and lane detection[J]. IEEE Trans. Image Processing, 1998, 7(1): 62-81.

[7] . Barron,D. Fleet,S. Beauchemin. Performance of optical flow techniques[J]. Computer Vision, 1994, 12(1): 43-77.

[8] Z. Sun,G. Bebis,R. Miller. On-road vehicle detection using gabor filters and support vector machines[C]. IEEE Digital Signal Processing,2002,2:1019-1022

[9] . Marola. Using symmetry for detecting and locating objects in a picture[J]. Computer Vision,Graphics,and Image Processing, 1989, 46(2): 179-195.

[10] C. Hoffmann,T. Dang,C. Stiller. Vehicle detection fusing 2D visual features [C]. IEEE Intelligent Vehicles Symposium,2004. 280-285

[11] . Avidan. Support vector tracking[J]. IEEE Transations on Pattern Analysis and Machine Intelligence, 2004, 26(8): 1064-1072.

[12] . McKenna,S. Jabri,Z. Duric et al.. Tracking groups of people[J]. Comput. Vis. Image Understanding, 2000, 80(1): 42-56.

[13] U. Regensburger,G. Volker. Visual recognition of obstacles on roads[C]. IEEE International Conference on Intelligent Robots and Systems,1994,2:980-987

[14] A. J. Lipton,H. Fujiyoshi,R. S. Patil. Moving target classification and tracking from real-time video[C]. IEEE Workshop Applications of Computer Vision,1998. 8-14

[15] . 单目视觉车道线识别算法及其ARM实现[J]. 南京航空航天大学学报, 2008, 40(2): 209-213.

. Monocular camera machine vision lane recognition algorithm and realization on ARM system[J]. J. Nanjing University of Aeronautics and Astronautics, 2008, 40(2): 209-213.

[16] H. Mori,N. M. Charkari. Shadow and rhythm as sign patterns of obstacle detection[C]. International Symposium on Industrial Electronics,1993,271-277

[17] C. Tzomakas,W. V. Seelen. Vehicle detection in traffic scenes using shadows[EB/OL],[1998-06],http:// citeseerx.ist.psu.edu/viewdoc/summary doi=10.1.1.45.2.

[18] S. Raboisson,P. Schmouker. Obstacle detection in highway envirment by color CCD camera and image processing prototype installed in a vehicle[C]. IEEE Symposium on Intelligent Vehicles,1994,44-49

[19] 曲兴华,何滢,韩峰等.强反射复杂表面随机缺陷检测照明系统分析[J]. 光学学报,2003,23(5):547-551

Qu Xinghua,He Ying,Han Feng et al.. Illumination system for detecting random defects on strongly reflective and complex surfaces[J]. Acta Optica Sinica,2003,23(5):547-551

[20] . Fukunaga,L. Hostetler. The estimation of the gradient of a density function,with applications in pattern recognition[J]. IEEE Trans. Information Theory, 1975, 21(1): 32-40.

[21] . Cheng. Mean shift,mode seeking,and clustering[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.

[22] . Comaniciu,P. Meer. Mean shift-A robust approach toward feature space analysis[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.

沈峘, 李舜酩, 柏方超, 缪小冬, 李芳培. 路面车辆实时检测与跟踪的视觉方法[J]. 光学学报, 2010, 30(4): 1076. Shen Huan, Li Shunming, Bo Fangchao, Miao Xiaodong, Li Fangpei. On Road Vehicles Real-Time Detection and Tracking Using Vision Based Approach[J]. Acta Optica Sinica, 2010, 30(4): 1076.

路面车辆实时检测与跟踪的视觉方法

关于本站 Cookie 的使用提示

全站搜索

路面车辆实时检测与跟踪的视觉方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索