Authors: Md. Khaliluzzaman; Kaushik Deb
Addresses: Department of Computer Science and Engineering (CSE), Chittagong University of Engineering and Technology (CUET), Chittagong-4349, Bangladesh ' Department of Computer Science and Engineering (CSE), Chittagong University of Engineering and Technology (CUET), Chittagong-4349, Bangladesh
Abstract: Stair region detection and distance estimation from a stair image are challenging activities to support visually impaired navigation safely in unknown environments. In this paper, a framework is proposed for detecting stair region from a stair image utilising some natural and unique property of a stair. One unique property of them is, every stair step's beginning and ending horizontal edge point intersects with two vertical edge points creating three connected point (TCP). The TCPs are used to validate the stair edge segments and calculate the vertical vanishing point to justify the stair edges. This justification ensures that validated edge segments are arranged in an increasing parallel order which is the other unique property of a stair. These increasing edge segments are verified by utilising the y coordinate value of the vanishing point and the detection of stair candidate region is confirmed by these properties. In addition, the triangular similarity is used for distance estimation from camera to stair. The proposed framework is tested using various stair images under a variety of conditions and results are presented to demonstrate the efficiency and effectiveness.
Keywords: autonomous stair climbing navigation; alarm system; Gabor filter; illumination; vanishing point; three connected point; TCP; triangular similarity.
International Journal of Computational Vision and Robotics, 2018 Vol.8 No.2, pp.168 - 189
Received: 05 Jan 2016
Accepted: 04 Aug 2016
Published online: 21 May 2018 *