Sea–sky line detection using gray variation differences in the time domain for unmanned surface vehicles

Abstract

Sea–sky lines (SKLs) can provide valuable reference information for the obstacle avoidance systems of unmanned surface vehicles (USVs) because obstacles that can threaten the safety of USVs, such as ships and rocks, are generally located below SKLs. Existing methods detect SKLs only using gray, texture or line features in an optical image. However, the background features in images obtained by onboard cameras are complex and change continuously over time, which leads to poor robustness of these methods. Conversely, the method that we proposed in this paper detects SKLs according to the gray variation differences in the time domain between the sky, the SKL and the sea surface when the USVs actually move on the sea. In this way, we can decrease the gray complexity of the image data of different backgrounds, which reduces interference while enhancing the edge features of the SKLs to obtain superior robustness. The proposed method is tested on optical image sequences collected by the ‘Jiu Hang 490’ USV. The experimental results demonstrate that the average accuracy of SKL detection is higher than that of existing methods with approximately 10% improvement while maintaining computational efficiency.