摘要 |
The performance of detecting the features of an object is to be improved. In one step, among pixels within a ROI, pixels whose feature amount is greater than a predetermined threshold value are extracted as a feature point candidate. In another step, a feature point density parameter is set based on a distance to an object within the ROI. In another steps, the feature points are extracted from the feature point candidates in the descending order of the feature amount, while the feature point candidates, whose distance from the extracted feature points is equal to or smaller than the feature point density parameter, are not extracted as the feature point. In another step, a feature point list representing the feature points extracted from the ROI is output. The present invention can be applied to an in-vehicle obstacle detecting device. |