A Survey on Water Hazard Detection in the Wild Field

Abstract

Autonomous off-road navigation is a highly complicated task for a robot or unmanned ground vehicle(UGV)owing to the different kinds of obstacles it could encounter.In recent years,many researches to detect the water bodies have been done.But there still has been very little work on detecting bodies of water that could be navigation hazards.In-particular,water hazards such as puddles and ponds are very common in wild field environments and are hard to detect even with ranging devices due to the specular nature of reflection at the air water interface.There are some environmental variables to be paid attention,such as ambient light,scene elements reflected by the surface,width of water surface and water depth.Depending on the different sensors,the algorithm technology of water hazard detection for autonomous off-road navigation is summarized,which are based on stereo vision,laser radar,color image segmentation,multi-feature based scheme,short-wave infrared(SWIR)imagery,thermal infrared imagery,polarization imaging technique and so on.The above methods related to the water hazard detection are introduced from two factors:ambient light and scene elements reflected by the surface in this paper.And the achievements of some research institutes are introduced for providing some reference to the development of domestic technology in this field.