Indoor place categorization using co-occurrences of LBPs in gray and depth images from RGB-D sensors

Jung, Hojung and Martinez Mozos, Oscar and Iwashita, Yumi and Kurazume, Ryo (2014) Indoor place categorization using co-occurrences of LBPs in gray and depth images from RGB-D sensors. In: Fifth International Conference on Emerging Security Technologies (EST-2014), 10-12 September 2014, University of Alcalá, Alcalá de Henares, Spain.

Documents
Indoor place categorization using co-occurrences of LBPs in gray and depth images from RGB-D sensors
[img]
[Download]
[img]
Preview
PDF
__ddat02_staffhome_jpartridge_jung2014est.pdf - Whole Document

426kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Indoor place categorization is an important capability for service robots working and interacting in human environments. This paper presents a new place categorization method which uses information about the spatial correlation between the different image modalities provided by RGB-D sensors. Our approach applies co-occurrence histograms of local binary patterns (LBPs) from gray and depth images that correspond to the same indoor scene. The resulting histograms are used as feature vectors in a supervised classifier. Our experimental results show the effectiveness of our method to categorize indoor places using RGB-D cameras.

Additional Information:Best Paper in the Machine Vision Workshop
Keywords:mobile robotics, robotic perception, place categorization, RGB-D sensors
Subjects:H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:14957
Deposited On:17 Sep 2014 08:07

Repository Staff Only: item control page