Research on Scalable Real-Time Image Mosaic Technology Based on Improved SURF

Abstract

Due to the presence of light and angle distortion, the image mosaic results is not ideal, which makes it difficult to identify subsequent ground object. To tackle this problem, this paper proposes an image mosaic technology based on the improved SURF (Speed-Up Robust Features) algorithm. After extracting image feature points, using Hessian matrix trace algorithm for image matching, and then the RANSAC algorithm purified the image feature point pairs. Finally, the image was stitched using a weighted smoothing algorithm. Experiments verify the effectiveness of this algorithm for image stitching with deviated scale and angle of view. At the same time, the algorithm is applied to the field of scalable real-time images stitching, and has achieved good results.