Research and Implementation of Binocular Image Stitching Algorithm Based on FPGA

The underwater environment is complex and variable. Light propagation is affected by multiple factors, such as water absorption and scattering. This often results in a lack of brightness in underwater images, which can hinder the extraction of image features and affect the matching of feature points between subsequent images. Given the aforementioned issues, this paper proposes the use of the FPGA platform in conjunction with the ORB algorithm to enhance the original feature extraction and descriptor generation algorithm. The goal is to improve the effectiveness of the feature extraction algorithm under varying light intensities. Additionally, a new 64-bit descriptor is designed using the parallelism of the FPGA. False matching points are removed through statistical analysis, ultimately achieving feature matching between two underwater images.