Vision-based corridor line detection using k-means algorithm

We propose a corridor lines extraction algorithm. The algorithm is based on a vision-system. It uses the patterns of slopes between two points, K-means, and least-square method. The proposed algorithm offers intersection lines between the wall and the floor. The proposed method consists of image preprocessing, noise filtering, and line extraction algorithm stage. The method has been tested on a large number of real corridor images. The experimental results are included to demonstrate the validity of the proposed algorithm.