Robust water hazard detection for autonomous off-road navigation  

作　　者：Tuo-zhong YAO Zhi-yu XIANG Ji-lin LIU 

机构地区：[1]Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China

出　　处：《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》2009年第6期786-793,共8页浙江大学学报（英文版）A辑（应用物理与工程）

基　　金：Project supported by the National Natural Science Foundation of China (Nos. 60505017 and 60534070);the Natural Science Foundation of Zhejiang Province, China (No. 2005C14008)

摘　　要：Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. Active learning is used for automatically dealing with problems caused by the selection, labeling and classification of large numbers of training sets. Mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ‘common’ water hazards, which usually have the features of both high brightness and low texture, but also ‘special’ water hazards that may have lots of ripples or low brightness.Existing water hazard detection methods usually fail when the features of water surfaces are greatly changed by the surroundings, e.g., by a change in illumination. This paper proposes a novel algorithm to robustly detect different kinds of water hazards for autonomous navigation. Our algorithm combines traditional machine learning and image segmentation and uses only digital cameras, which are usually affordable, as the visual sensors. Active learning is used for automatically dealing with prob- lems caused by the selection, labeling and classification of large numbers of training sets. Mean-shift based image segmentation is used to refine the final classification. Our experimental results show that our new algorithm can accurately detect not only ＇common＇ water hazards, which usually have the features of both high brightness and low texture, but also ＇special＇ water hazards that may have lots of ripples or low brightness.

关 键 词：Water hazard detection Active leaming ADABOOST MEAN-SHIFT 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程] V448.224[自动化与计算机技术—控制科学与工程]