Effective Waterline detection for unmanned surface vehicles in inland water

Abstract

In the maritime environment, real-time and accurate water line detection can help unmanned surface vehicles (USVs) for autonomous navigation. Special features such as cloud clutter, water reflection, water surface glint and background texture in optical images make it very difficult for USV to detect the water line accurately. To address this problem, a novel water line detection approach is proposed for a practical USV system in the inland water. In this paper, land-water and sky-water line are taken into consideration as part of the water line. To minimize the influence of background texture, the local variation method is introduced to smooth the image and remain the background structure, such as the water line. Regarding the linear characteristic, these water line points are constrained near a line by the RANSAC algorithm. The experimental results are given in the end and show that the proposed approach is effective and can be applied to different environments.