Accurate 3D-vision-based obstacle detection for an autonomous train

In this paper we present a 3D-vision based obstacle detection system for an autonomously operating train in open terrain environments. The system produces dense depth data in real-time from a stereo camera system with a baseline of 1.4m to fulfill accuracy requirements for reliable obstacle detection 80m ahead. On an existing high speed stereo engine, several modifications have been applied to significantly improve the overall performance of the system. Hierarchical stereo matching and slanted correlation masks increased the quality of the depth data in a way that the obstacle detection rate increased from 89.4% to 97.75% while the false positive detection rate could be kept as low as 0.25%. The evaluation results have been obtained from extensive real-world test data. An additional stereo matching speed-up of factor 2.15 was achieved and the overall latency of obstacle detection is considerably faster than 300ms.

[1]  Romuald Aufrère,et al.  Accurate road following and reconstruction by computer vision , 2002, IEEE Trans. Intell. Transp. Syst..

[2]  Alberto Broggi,et al.  Obstacle Detection with Stereo Vision for Off-Road Vehicle Navigation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[3]  Carsten Rother,et al.  PatchMatch Stereo - Stereo Matching with Slanted Support Windows , 2011, BMVC.

[4]  Christian Zinner,et al.  Off-road Terrain Mapping Based on Dense Hierarchical Real-Time Stereo Vision , 2012, ISVC.

[5]  Xi Yang,et al.  Advance in vision-based driver assistance , 2011, 2011 International Conference on Electric Technology and Civil Engineering (ICETCE).

[6]  Kristian Ambrosch,et al.  An Optimized Software-Based Implementation of a Census-Based Stereo Matching Algorithm , 2008, ISVC.

[7]  Ralph Ross,et al.  Vision-based track estimation and turnout detection using recursive estimation , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[8]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[9]  Yi-Ping Hung,et al.  Multipass hierarchical stereo matching for generation of digital terrain models from aerial images , 1998, Machine Vision and Applications.

[10]  Linda G. Shapiro,et al.  Computer Vision , 2001 .

[11]  Darius Burschka,et al.  Stereo-based obstacle avoidance in indoor environments with active sensor re-calibration , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[12]  William Travis,et al.  SciAutonics-Auburn Engineering's low-cost high-speed ATV for the 2005 DARPA grand challenge , 2006 .

[13]  Ho Gi Jung,et al.  Stereo Vision Based Advanced Driver Assistance System , 2005 .

[14]  R. Danescu,et al.  A Sensor for Urban Driving Assistance Systems Based on Dense Stereovision , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[15]  Larry H. Matthies,et al.  Attenuating stereo pixel-locking via affine window adaptation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[16]  Markus Vincze,et al.  A fast stereo matching algorithm suitable for embedded real-time systems , 2010, Comput. Vis. Image Underst..

[17]  Jean-Philippe Tarel,et al.  Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[18]  Sanjiv Singh,et al.  Obstacle detection using adaptive color segmentation and color stereo homography , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[19]  Wolfgang Pree,et al.  Autonomously Driving Trains on Open Tracks — Concepts, System Architecture and Implementation Aspects , 2012, it Inf. Technol..

[20]  Pilar Bachiller Burgos,et al.  Multi-cue visual obstacle detection for mobile robots , 2010 .

[21]  Andreas Uhl,et al.  Track Detection for Autonomous Trains , 2010, ISVC.

[22]  Nicolas Ventroux,et al.  Stereovision-based 3D obstacle detection for automotive safety driving assistance , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[23]  Stefano Ghidoni,et al.  Multi Stereo-Based Pedestrian Detection by Daylight and Far-Infrared Cameras , 2009 .

[24]  Steven W. Zucker,et al.  Stereo for Slanted Surfaces: First Order Disparities and Normal Consistency , 2005, EMMCVPR.