Stairway Detection Based on Extraction of Longest Increasing Subsequence of Horizontal Edges and Vanishing Point

TLDR: In this paper, a framework is proposed for detecting stairway regions from stair images using a natural property of stair, where steps of a stair appear sorted by their length from top to bottom of the stair.

Abstract: Detection of stair region from a stair image is very crucial for autonomous climbing navigation and alarm system for blinds and visually impaired. In this regard, a framework is proposed in this paper for detecting stairways from stair images. For detection of the stair region, a natural property of stair is utilized that is steps of a stair appear sorted by their length from top to bottom of the stair. Based on this idea, initially, horizontal edge detection is performed on the stair image for detecting stair edges. In second step, longest horizontal edges are extracted from the edge image through edge linking. In third step, longest increasing subsequence (LIS) algorithm is applied on the horizontal edge image for extracting stair edge. Finally, the vanishing point is calculated from these sets of horizontal lines to confirm the detection of stair candidate region. Various stair images are used with a variety of conditions to test the proposed framework and results are presented to prove its effectiveness.