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.