Optical Sources Optimization for 3D Reconstruction Based on Underwater Vision System

摘要

This paper presents an optimization algorithm of optical sources based on an underwater camera model. We explore underwater visual 3D reconstruction in a completely dark environment with proposed optimization algorithm. The image model of underwater camera incorporates parameters on optical sources, water effects and the underwater camera, which forms a systematic underwater model. Then an energy function is defined on the basis of the model to compute energy values of all images in different orientations. The best energy value of the image represents optimal optical sources' configuration and direction with predefined flying altitude by using the optimization algorithm. To validate the algorithm, the underwater stereo vision system has been set up to explore the 3D reconstruction scheme of the underwater environment at small scale and high density. The results have shown that the proposed method for optical sources optimization has good performance.