Safety of stereo driver assistance systems

The discrete nature of disparities observed by stereo systems results in complex behaviour of speeds measured by them and affects the efficacy of a stereo based driver assistance system. We describe a tool for a safety engineer which permits the safety of these systems to be estimated. It is based on a model which considers the true error in measured velocities of objects. Outputs from this tool show that choice of stereo system parameters so as to judiciously place the disparity change boundaries is critical to the effectiveness of such a system because the range of possible trajectories for a (possibly colliding) object reduces significantly when a feature point on that object crosses one of these boundaries. This factor also means that larger objects (e.g. trucks) are slightly better tracked by stereo than smaller ones (e.g. signs and pedestrians). Completely safe stereo based systems are also shown to issue many precautionary (and ultimately unnecessary) warnings if the stereo parameters are not chosen carefully.

[1]  Larry H. Matthies,et al.  Error modeling in stereo navigation , 1986, IEEE J. Robotics Autom..

[2]  Shun-Chung Wang,et al.  Study on vehicle safety distance warning system , 2008, 2008 IEEE International Conference on Industrial Technology.

[3]  Hong Jeong,et al.  A fast and parallel belief computation structure for stereo matching , 2007 .

[4]  Massimo Bertozzi,et al.  Stereo vision-based vehicle detection , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[5]  Antony Tang,et al.  Collision avoidance timing analysis of DSRC-based vehicles. , 2010, Accident; analysis and prevention.

[6]  Uwe Franke,et al.  Performance Evaluation of Stereo Algorithms for Automotive Applications , 2009, ICVS.

[7]  D E Fumi,et al.  A novel in-vehicle real-time brake-monitoring system , 2009 .

[8]  Georgy L. Gimel'farb,et al.  Intelligent Vision: A First Step - Real Time Stereovision , 2009, ACIVS.

[9]  John Richardson,et al.  The influence of alarm timing on driver response to collision warning systems following system failure , 2006, Behav. Inf. Technol..

[10]  Reinhard Klette,et al.  Stereo accuracy for collision avoidance , 2009, 2009 24th International Conference Image and Vision Computing New Zealand.

[11]  Allen R. Hanson,et al.  Computer Vision Systems , 1978 .

[12]  Avinash C. Kak,et al.  Vision for Mobile Robot Navigation: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  John Richardson,et al.  The influence of alarm timing on braking response and driver trust in low speed driving , 2005 .

[14]  Per Wramborg A New Approach to a Safe and Sustainable Road Structure and Street Design for Urban Areas , 2005 .

[15]  R E Dewar,et al.  PERCEPTION AND INFORMATION PROCESSING. IN: HUMAN FACTORS IN TRAFFIC SAFETY , 2002 .

[16]  John Morris,et al.  Verging Axis Stereophotogrammetry , 2011, PSIVT.