Indoor Place Categorization Using Co-occurrences of LBPs in Gray and Depth Images from RGB-D Sensors

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.