An Improved UAV Aerial Image Mosaic Algorithm Based on GMS-RANSAC

The aerial image mosaic algorithm needs to ensure the real-time performance of the algorithm and the natural transition of image fusion. In order to improve the matching performance of the algorithm, an improved UAV aerial image registration algorithm based on GMS-RANSAC is proposed. The improved algorithm introduces the idea of partitioning, divides the image into meshes and then performs feature extraction on each mesh, uses the bidirectional BF algorithm and the GMS algorithm to perform accurate feature value matching, and finally uses the improved RANSAC algorithm for further feature purification to obtain a high-quality correct interior point set. This paper combines the characteristics of GMS algorithm to improve the RANSAC algorithm, reduce the number of iterations of the algorithm, and reduce the time complexity of the algorithm. The improved image registration algorithm has higher accuracy and shorter running time. After the registration is completed, the image is merged to obtain a mosaic image.