Home > Explore Content > All Issues > Article View
Indoor environment recognition based on depth image
Journal of The Korea Society of Computer and Information
Abbr :
JKSCI
2014, 19(11), pp.53-61
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science
2014, 19(11), pp.53-61
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science
-
In this paper, we propose a method using an image received by the depth camera in order to separatethe wall in a three-dimensional space indoor environment. Results of the paper may be used to providevaluable information on the three-dimensional space. For example, they may be used to recognize theindoor space, to detect adjacent objects, or to project a projector on the wall. The proposed method firstdetects a normal vector at each point by using the three dimensional coordinates of points. The normalvectors are then clustered into several groups according to similarity. The RANSAC algorithm is applied toseparate out planes. The domain knowledge helps to determine the wall among planes in an indoorenvironment. This paper concludes with experimental results that show performance of the proposed method in various experimental environment.
131 Viewed
Print this page
Download PDF