|
|
Obstacle detection based on V-intercept in disparity space |
CAO Teng, XIANG Zhi-yu, LIU Ji-lin |
Department of Information Science and Electronic Engineering, Zhejiang Provincial Key Laboratory of Information Network Technology, Zhejiang University, Hangzhou 310027, China |
|
|
Abstract A new analysis method of obstacles in the disparity space with “V-intercept” concept was proposed in order to analyze the environment around stereo vision based driving systems more effectively, Unlike the traditional methods which detected the obstacles in 3D space, this method worked directly in the disparity space, converting the obstacles slope information into intercept on V axis in disparity space to achieve detection. Conversion relationship between slope and intercept was derived in the disparity space, and reasonable threshold interval was determined. The whole detection algorithm was fast and efficient, and was not affected by the assumption of flat road from the principle, giving a strong practical value. Experiments in multiple environments showed that result of this method was reliable and stable, which was 3.9 times faster than that of 3D space based method.
|
Published: 28 August 2015
|
|
基于视差空间V-截距的障碍物检测
为了更加高效地完成对基于双目立体视觉的驾驶系统的环境分析,提出新的应用于视差空间中分析障碍的“V-截距”方法.与传统在三维空间中的障碍检测方法不同,该方法直接在视差空间中进行检测,通过将障碍坡度信息转换为视差空间中V轴的截距实现检测.推导视差空间中的坡度-截距转换关系,划定合理的阈值区间.整个检测算法具有快速高效的特点,在原理上不受平面道路的假设约束,具有很强的实际应用价值.多种环境下的实验证明:该方法的障碍物检测效果可靠、稳定,检测速度是基于三维空间的方法的3.9倍.
|
|
[1] FRANKE U, GAVRILA D, GORZIG S, et al. Autonomous driving goes downtown [J]. Intelligent Systems and Their Applications, IEEE, 1998, 13(6): 40-48.
[2] BERTOZZI M, BROGGI A. GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection [J]. IEEE Transactions on Image Processing, 1998, 7(1): 62-81.
[3] LABAYRADE R, AUBERT D, TAREL J P. Real time obstacle detection in stereovision on non flat road geometry through “V-disparity” representation [C]∥ Intelligent Vehicle Symposium. Versailles: IEEE, 2002, 2: 646-651.
[4] LABAYRADE R, AUBERT D. A single framework for vehicle roll, pitch, yaw estimation and obstacles detection by stereovision[C]∥Intelligent Vehicles Symposium. Columbus: IEEE, 2003: 31-36.
[5] HU Z, UCHIMURA K. U-V-disparity: an efficient algorithm for stereovision based scene analysis [C]∥ Intelligent Vehicles Symposium. Nevada: IEEE, 2005: 48-54.
[6] DEMIRDJIAN D, DARRELL T. Motion estimation from disparity images[C]∥ 8th IEEE International Conference on Computer Vision. Vancouver: IEEE, 2001, 1:213-218.
[7] PFEIFFER D, FRANKE U. Modeling dynamic 3D environments by means of the stixel world [J]. Intelligent Transportation Systems Magazine. 2011, 3(3): 24-36.
[8] PFEIFFER D, FRANKE U, DAIMLER A G. Towards a global optimal multi-layer stixel representation of dense 3D data [C]∥ Proceedings of the British Machine Vision Conference. Dundee: BMVA Press, 2011: 112.
[9] PFEIFFER D, ERBS F, FRANKE U. Pixels, stixels, and objects [C]∥ 12th European Conference on Computer Vision Workshops and Demonstrations. Berlin Heidelberg: Springer, 2012: 110.
[10] GEIGER A, LENZ P, STILLER C, et al. Vision meets robotics: the KITTI dataset [J]. International Journal of Robotics Research, 2013, 32(11): 1231-1237.
[11] HIRSCHMULLER H. Stereo processing by semiglobal matching and mutual information [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(2): 328-341. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|