The recovery of optical flow for intelligent cruise control

This paper describes the analysis of optical flows computed on image sequences taken by a TV camera mounted on a car moving in usual outdoor sceneries. The vibration of the TV camera makes the numerical computation of temporal derivatives very noisy and the texture of the road image is very poor. Therefore differential techniques do not provide adequate results. By using correlation based techniques and by correcting the optical flows for shocks and vibrations, useful sequences of optical flows can be obtained. When the car is moving along a flat road and the optical axis of the TV camera is parallel to the ground, the motion field is expected to be quadratic and have a specific structure: as a consequence the egomotion can be estimated from this optical flow and information on the absolute velocity, angular velocity and radius of curvature of the moving vehicle can be obtained. In addition it is shown how to detect the relative motion caused by another moving vehicle, either approaching or overtaking. These results suggest that the optical flow can be successfully used by a vision system for assisting a driver in a vehicle moving in usual streets and motorways.

[1]  Reinhold Behringer,et al.  An all-transputer visual autobahn-autopilot/copilot , 1993, 1993 (4th) International Conference on Computer Vision.

[2]  Toshio Ito,et al.  An extracting method of the optical flow for an anticollision system , 1992 .

[3]  Ernst D. Dickmanns,et al.  Recursive 3-D Road and Relative Ego-State Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Martial Hebert,et al.  Vision and navigation for the Carnegie-Mellon Navlab , 1988 .

[5]  H. Inoue,et al.  Automated Vehicle System Using Both A Computer Vision And Magnetic Field Sensors , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[6]  Alessandro Verri,et al.  Motion analysis from first-order properties of optical flow , 1992, CVGIP Image Underst..

[7]  Wilfried Enkelmann,et al.  Obstacle detection by evaluation of optical flow fields from image sequences , 1990, Image Vis. Comput..

[8]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[9]  Patrick Bouthemy,et al.  Multimodal Estimation of Discontinuous Optical Flow using Markov Random Fields , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Vincent Torre,et al.  Localization and Noise in Edge Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Henry Schneiderman,et al.  Real-time Visual Processing For Autonomous Driving , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[12]  Volker Graefe,et al.  Vision For Intelligent Road Vehicles , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[13]  Hidetoshi Miike,et al.  Determining optical flow from sequential images , 1988, Systems and Computers in Japan.

[14]  Jan-Olof Eklundh,et al.  Object detection using model based prediction and motion parallax , 1990, ECCV.

[15]  Takeo Kanade,et al.  The new generation system for the CMU Navlab , 1992 .

[16]  F. Bartolini,et al.  Multiwindow least-squares approach to the estimation of optical flow with discontinuities , 1993 .

[17]  Yiannis Aloimonos,et al.  Obstacle Avoidance Using Flow Field Divergence , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Martin Herman,et al.  New visual invariants for obstacle detection using optical flow induced from general motion , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[19]  T. Morita,et al.  An Approach To The Intelligent Vehicle , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[20]  E. De Micheli,et al.  Vehicle Guidance From One Dimensional Optical Flow , 1993, Proceedings of the Intelligent Vehicles '93 Symposium.

[21]  Vincent Torre,et al.  The Accuracy of the Computation of Optical Flow and of the Recovery of Motion Parameters , 1993, IEEE Trans. Pattern Anal. Mach. Intell..