Research on image mosaic of low altitude UAV based on harris corner detection

Low-altitude UAV image acquisition has the characteristics of high resolution, but its field of view is narrow. The shortcomings of narrow field of view can be solved by image mosaic of low-altitude UAV. This study combines Harris corner detection algorithm, adaptive non-maximal suppression algorithm, then the transformation matrix is calculated by using RANSAC algorithm, removing the mismatched feature point pairs, finally, a weighted average image fusion algorithm based on gradual-in and gradual-out is used to fused image, the image mosaic of UAV with 80% overlap rate and 130.6 meters low altitude was completed. The experimental results show that after using this algorithm, the meaningless corners are removed, the local representative corners are retained, and the detection time of corners is reduced by 30.2%. This algorithm improves the stitching speed.