Image-based dynamic measurement for vehicle steering control

An image sensing technique is developed in this study using image plane analysis to measure the dynamic motion variables of a vehicle based on the road scene viewed from a camera inside the vehicle. Some motion variables such as heading angle, lateral deviation, yaw rate, and sideslip angle of the vehicle are measured and could be further used for steering control systems such as automatic steering and four-wheel steering system. An experimental car is set up to verify the image sensing method. The vehicle is equipped with a V8 video camera to record the road scene viewed from a moving vehicle. To examine the proposed image sensing method, other measuring process is utilized to manually measure the motion variables based on the traces of the vehicle left on the road. The recorded video data are used to test the image sensing technique in an off-line manner in the laboratory to obtain motion information. Some experimental results for the situation of straight road show that the proposed sensing technique is feasible.