IMAGE PROCESSING DEVICE AND METHOD, DRIVING SUPPORT SYSTEM, AND VEHICLE

摘要

While extracting four feature points from a camera image obtained from a camera installed in a vehicle, an image processing device sets the positions of four reference points on an offset correction image to be generated from the camera image and performs a coordinate conversion based on a homography matrix so that the coordinate values of the four feature points are converted to the coordinate values of the four reference points. The image processing device sets each of the coordinate values so that an image center line and a vehicle center line are matched with each other on the offset correction image. The image processing device determines whether or not an image lacking area in which image data based on the image data of the camera image is not present is included within the entire area of the generated offset correction image. If the image lacking area is included, the two reference points or the four reference points are symmetrically moved in the left and right directions and the homography matrix is recalculated according to the positions of the reference points after the movement.