A Calibration Method for Underwater Stereo Vision System

Abstract

The invention discloses a method for calibrating an underwater stereo vision system, comprising the following steps: S101. In an underwater environment, use a stereo vision system composed of cameras with known internal parameters to capture images of several plane calibration plates, and extract the images and perform distortion correction on the feature points; S102, construct a cost function according to the geometric relationship of the refraction light path, arbitrarily select a camera in the stereo vision system and calibrate the refraction parameters of the camera; S103, according to the completed calibration The refraction parameters of the camera are calibrated based on the above cost function to calibrate the refraction parameters of the uncalibrated camera in the stereo vision system and the external parameters of the stereo vision system. The invention uses a plane calibration plate, which improves the calibration accuracy; based on the multi-layer refraction model, there is no systematic error, and the description accuracy is high, which can not only be used for the refraction parameter calibration of an underwater single camera, but also can be used for underwater stereo vision systems and other systems. Calibration of refractive parameters and extrinsic parameters for underwater multi-camera systems.

Description

technical field [0001] The invention relates to the technical field of underwater camera calibration, in particular to a calibration method for an underwater stereo vision system. Background technique [0002] In the underwater environment, the imaging light will pass through the three layers of refraction media: water, filter, and air. Existing methods often apply the traditional camera model to this refraction system, and use radial distortion coefficients to correct the deviation caused by refraction. However, the influence of refraction on the deviation of different pixels is different, and using the traditional camera model will produce obvious errors, especially in an environment with a high refractive index such as underwater. Traditional underwater camera calibration generally has the problems of complicated calibration methods, long calibration time, low calibration accuracy, and inability to perform underwater stereo vision calibration. Contents of the invention...

AI Technical Summary

Problems solved by technology

However, the influence of refraction on the deviation of different pixels is different, and using the traditional camera model will produce obvious errors, especially in an environment with a high refractive index such as underwater

Traditional underwater camera calibration generally has the problems of complex calibration methods, long calibration time, low calibration accuracy, and inability to perform underwater stereo vision calibration.

Images