基于偏振信息的水体障碍物检测方法

将光的偏振概念引入机器视觉领域，并应用于智能机器人野外导航中水体障碍物的检测.该方法基于如下物理准则：非偏振光通过平滑水面反射后成为部分线性偏振光，其偏振相位相对周围环境具有更大的相似性.通过综合比较偏振度的大小和偏振相位的相似性，可以检测出场景中的水体障碍物.实验结果表明，该方法对复杂自然环境下水体障碍物的检测，特别是包含周围植物倒影的水体部分的检测具有良好的效果.与传统机器视觉方法相比，偏振视觉手段计算简单，可以与现有图像处理技术结合使用.

Polarization-based water obstacle detection method

The concept of polarization was introduced into computer vision to detect water obstacles for autonomous off-road navigation.This method is based on the physical principle that the light reflected from water surface are partial linearly polarized and their polarization phases are more similar than those from the scenes around.Water obstacles were detected by comparison of polarization degree and similarity of polarization phases.Experimental results show that the method has good performance in water obstacle detection in complex natural backgrounds,especially when there is vegetation reflected in the water.Compared to the traditional computer vision techniques,the method is computationally efficient and can be easily implemented with the existing image processing technology.