Underwater target ranging method based on binocular vision

Abstract

The invention discloses an underwater target ranging method based on binocular vision, and belongs to the field of computer vision, the method comprises the following steps: an improved underwater calibration algorithm is adopted to calibrate a camera and obtain internal and external parameters of the camera, and obtain a binocular image after underwater target correction; stereo matching is carried out by using the corrected binocular image to obtain an image parallax error; the angular point depth is obtained through similar triangle original solution calculation by utilizing the obtained image parallax; the distance test of the underwater target is completed. Based on an air binocular ranging algorithm, an underwater imaging model of a camera is combined, the influence of underwater factors on camera calibration is more comprehensively considered, factors such as the refractive index are added, the image correction capability of the camera during underwater work is enhanced, an improved Harris corner detection algorithm is adopted, the clustering phenomenon of underwater image corners can be relieved, selection of thresholds in the algorithm is avoided, mismatching points are reduced, and the accuracy and precision of image matching are improved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an underwater target ranging method based on binocular vision. Background technique [0002] The biggest difference between the terrestrial binocular vision system and the underwater binocular vision system is that the propagation medium of the light has changed. The camera and the shooting object on land are in the air, while in the underwater imaging process, the shooting object is underwater, and the Two cameras placed in parallel must be in the air, the optical axis of the camera is perpendicular to the interface, and the two are placed in parallel, separated by a transparent waterproof glass cover in the middle, and the light will occur at the interface of different media during the propagation process. The phenomenon of refraction affects the accuracy of calibration of internal and external parameters. Therefore, subsequent modeling and experiments should consider the influe...

AI Technical Summary

Problems solved by technology

The calibration model in the air has been perfected, but there is no fixed calibration method and model for the underwater environment

At present, most underwater binocular ranging methods follow the binocular algorithm in the air, and do not improve the algorithm in combination with underwater imaging problems.

Images