| 摘要 |
PURPOSE: To comparatively accurately recognize an obstacle with a simplified logic by expanding the black area of an inputted monochromatic image, performing binarization after this expansion and dividing this image into a white area and the black area. CONSTITUTION: This method is composed of a monochromatic camera 1 for monitor installed at a prescribed position in a its own vehicle such as near a back mirror, for example, for picking the image in front of the vehicle, image processing 2 for fetching monochromatic image information picked up by this camera 1 and performing required image processing, and computer 3. First of all, the black part in the picked-up monochromatic image is expanded. Next, this monochromatic image is binarized and divided into the black area and the white area and noise such as a small point is removed. After the noise is removed, the likeness of the decided black area to be vehicle is checked and the information other than the vehicle is removed. Namely, it is checked whether the relevant black area is the vehicle (obstacle) or not. |
