A least square matching optimization method of low altitude remote sensing images based on self-adaptive patch

This paper presents a novel matching optimization method based on self-adaptive template. The proposed method is designed to be effective for enhancing the accuracy of stereo matching. In order to improve the similarity of the initial matching windows and fully exploit the pixels around the corresponding image points, a self-adaptive patch is introduced instead of a constant patch. Then, an error equation is built to compute the optimal point according to space geometry relationship and epipolar line constraint. At last, a least square adjustment method is used to calculate the coordinate of the corresponding 3D point in the Object Space Coordinate System. Comparison studies and experimental results prove the high accuracy of the proposed algorithm in low-altitude remote sensing image point cloud optimization.