Corridor Line Detection for Vision Based Indoor Robot Navigation

Abstract

The capability of a mobile robot to negotiate corridors is essential for autonomous navigation in an indoor environment. An approach is proposed for determining the corridor line locations and the vanishing point in a corridor environment using a single camera, based on hypotheses generation/verification and a feedback control strategy. A corridor line is the intersection line between a wall and the floor, which is, the farthest lateral position the autonomous robot can safely navigate in a corridor. There have been numerous approaches described in the literature which detect corridor edges and vanishing point; however, no solution has been reported to detect true corridor line locations in the presence of many spurious linear features around the corridor line. The proposed method consists of low, medium, and high level processing stages which correspond to the extraction of features, the formation of hypotheses, and the verification of hypotheses using a feedback mechanism, respectively. The system has been tested on a large number of real corridor images captured by a moving robot in a corridor. The experimental results demonstrated the reliability and robustness of the approach with respect to different viewpoints, reflection variations and different illumination conditions