VISION-BASED MOTION MEASUREMENT BY DIRECTLY EXTRACTING IMAGE FEATURESFOR VEHICULAR STEERING CONTROL

An image sensing technique is developed using image plane analysis to measure the vehicular motion variables through an in-vehicle camera. A new measurement model is derived to directly connect the image featur es of vanishing point and base point with the desired motion variables comprising heading angle, lateral deviation, yaw rate and sideslip an gle of the vehicle. These are useful in vehicular steering control app lications such as automatic and four-wheel steering systems for provid ing feedback motion information in a convenient way. In order to test the proposed vision-based measuring scheme, a computerized road scene is simulated as the test sample using a newly proposed model for curva ture-based road generation. Finally, experimental works are performed using the real road scene to verify the image sensing method. Consiste nt results are obtained by comparing with other measurements from a ya w rate gyro and from vehicular traces left on the road.