A Real-time Stitching Algorithm for UAV Aerial Images

Real-time stitching is a research focus of UAV area. The speed and accuracy of stitching algorithm are both important for commanders to make right decisions in battlefield. In this paper, a real-time UAV aerial image stitching algorithm based on predicted region matching is proposed. A new matching strategy is applied to the feature matching step. The transformation matrix will be calculated by the matches between features in current image and features in a predicted region. Experimental results show that, comparing with traditional method, the new algorithm can reduce much stitching errors while keeping the process time almost the same.