Stairways detection based on approach evaluation and vertical vanishing point
by Md. Khaliluzzaman; Kaushik Deb
International Journal of Computational Vision and Robotics (IJCVR), Vol. 8, No. 2, 2018

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.

Online publication date: Thu, 24-May-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Vision and Robotics (IJCVR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com