FPGA-based real-time panoramic image mosaic method

Abstract

The invention provides an FPGA-based real-time panoramic image mosaic method. The method is characterized by, to begin with, carrying out gray conversion on collected video data; then, extracting feature points of each frame image in a video stream through a Harris corner detection method; after obtaining corner coordinates of the front-back two frame images, carrying out calculation on regions with corners as centers respectively through an NCC-SSDA fusion algorithm to find out the correspondence relation between the feature points of the two frame images; removing unmatched point pairs through an RANSAC algorithm, estimating affine transform model parameters, finding an optimum model and taking all of local inner points according with the model as the final matching result; and finally, carrying out fusion on image edges through a weighted smoothing algorithm, and seamlessly displaying images after mosaic. The method can quickly finish single-camera 360-degree panoramic mosaic, and has the advantages of high registration accuracy, high real-time performance and good stability.

Description

technical field [0001] The invention belongs to the field of real-time panoramic image stitching, and in particular relates to an FPGA-based real-time panoramic image stitching method. Background technique [0002] Image mosaic is an increasingly popular research field, which refers to the spatial matching and alignment of multiple images of the same scene with overlapping parts, and after resampling and fusion, a wide-view image containing the information of each image sequence is formed. A complete, high-definition panorama of the scene. Image stitching is widely used in the fields of computer vision, image processing, computer, graphics, medical image analysis and virtual reality. [0003] The key to image stitching is image matching. Image matching techniques include: matching based on image grayscale, matching based on features and matching based on transform domain. Among them, the feature-based matching uses some points, lines or edges with a small number and stabl...

AI Technical Summary

Problems solved by technology

[0004] Document 1 (Zheng Zhibin, Ye Zhongfu. An image mosaic method based on Harris corner features, 2010,36(10):23-25.) Firstly, the Harris corner detection algorithm is used to extract the feature points, and then the normalized correlation method is used to Carry out initial matching, and then introduce Mahalanobis distance to realize fine matching of images. Although the algorithm is simple, the accuracy needs to be improved; Literature 2 (Li Bolin, Research on Registration Algorithm Based on Feature Point Image Mosaic: [Master's Thesis] Tianjin University 2008) will The fine matching part is replaced by the RANSAC algorithm, but RANSAC must perform enough sampling in a serial iterative manner to ensure the success rate, the operation speed is limited, and further simplification and improvement are needed to achieve real-time effects

Images