Function mola::vision::goodFeaturesToTrack
Defined in File feature_detection.h
Function Documentation
-
std::vector<mrpt::math::TPoint2Df> mola::vision::goodFeaturesToTrack(const mrpt::img::CImage &img, const GoodFeaturesParams ¶ms = {})
Shi-Tomasi (or Harris) corner detector.
Algorithm:
Compute Sobel gradients Ix, Iy.
Compute structure tensor entries Ix², IxIy, Iy² via box-filter (block_size).
Score = min eigenvalue of tensor (Shi-Tomasi) or det−k·trace² (Harris).
Non-maximum suppression in a (min_distance×min_distance) window.
Threshold by quality_level * max_score.
Sort by score descending, return top max_corners.
Input: grayscale CH_GRAY D8U image. Output: pixel coordinates as TPoint2Df (col=x, row=y), sorted by score.
Adapted from: lightweight_vio (MIT License), goodFeaturesToTrack logic.