A Robust Obstacle Detection Method in Highly Textured Environments Using Stereo Vision

Abstract

Stereo vision based obstacle detection is an algorithm that aims to detect and compute obstacle depth using stereo matching and disparity map. This paper presents a robust method to detect positive obstacles including staircases in highly textured environments. The proposed method is easy to implement and fast enough for obstacle avoidance. This work is partly inspired by the work of Nicholas Molton et al [1]. The algorithm consists of several steps including calibration, pre processing, obstacle detection, analysis of disparity map and depth computation. This method works well in highly textured environments and ideal for real applications. An adaptive thresholding is also applied for better noise and texture removal. Experimental results show the effectiveness of the proposed method.