Adaptive Weight Multi-band Blending Based Fast Aerial Image Stitching and Mapping

In this paper, we implement a real-time method for incrementally stitching aerial images over a large area. To collect high-quality aerial images, the camera is mounted on a gimbal. Being isolated from the vibration of the drone, the camera can provide relatively stable and less blurry images. To achieve fast aerial mapping, instead of using traditional feature extraction and matching steps, this algorithm only relies on camera position and orientation for blending. The mosaic is fused and incrementally updated based on the adaptive weight multi-band blending algorithm. The weight matrix and Laplacian pyramid for blending are updated adaptively. The orthoimage can be reconstructed from the Laplacian pyramid incrementally. This method was applied in the aerial mapping task of the ninth International Micro Air Vehicle Conference and Flight Competition, achieving a high quality map that contributed to the team's championship in the outdoor competition.