| 摘要 |
An on-vehicle image processing apparatus includes: an image taking apparatus for taking an image of a forward view of a vehicle; an edge detection section for generating a detection image data based on the image data; and a feature point detection section for detecting at least one feature point based on the detection image data. The feature point detection section categorizes the at least one feature point into a lane division line feature point, a branch feature point, and a dead end and obstacle feature point. The detection image data includes a lane division line detection scanning region set in a near region from the vehicle, a branch detection scanning region set in a middle region from the vehicle, and a dead end and obstacle detection scanning region set in a far region from the vehicle. The amount of scanning process can be reduced. |
