Hybrid Feature Enhance Filter (HFEF) for Underwater Vision Navigation

摘要

This research presents a real-time visibility enhancement algorithm for effective underwater visual navigation. Unlike an aerial environment, an underwater environment is a poor visibility as light travels in the water and the resulting scenes are poorly contrasted and hazy. At present, several vision-based navigation algorithms were introduced by the ground robotic communities. However, most of them fail in underwater due to image degradation. But, there is a possibility to use the same vision navigation methods with image preprocessing which addresses image degradation. Presented paper address the turbidity of the water, the most common problem in underwater image preprocessing, and improved feature point detection and matching which can be used in a vision-based navigation algorithm effectively. The proposed enhancement method combining with, noise removing, artificial light estimation, de-hazing, adaptive depth aware contrast stretching, and image sharpening. The proposed method is validated using two underwater turbidity datasets, one for different turbidity levels and one for visual SLAM with OpenVSLAM. The result showed the proposed visibility enhancement algorithm improved the underwater visual SLAM navigation significantly.