Joint Color-Spatial-Directional clustering and Region Merging (JCSD-RM) for unsupervised RGB-D image segmentation

Abul Hasnat (1) , Olivier Alata (1) , Alain Treméau (1)

1 LHC - Laboratoire Hubert Curien

Recent advances in depth imaging sensors provide easy access to the synchronized depth with color, called RGB-D image. In this paper, we propose an unsupervised method for indoor RGB-D image segmentation and analysis. We consider a statistical image generation model based on the color and geometry of the scene. Our method consists of a joint color-spatial-directional clustering method followed by a statistical planar region merging method. We evaluate our method on the NYU depth database and compare it with existing unsupervised RGB-D segmentation methods. Results show that, it is comparable with the state of the art methods and it needs less computation time. Moreover, it opens interesting perspectives to fuse color and geometry in an unsupervised manner.

Keywords: Unsupervised Clustering; RGB-D image segmentation; Directional distributions; Bregman divergence; Mixture model; Region adjacency graph; Region merging

Domains: Computer Science [cs]; Signal and Image Processing

Abul Hasnat, Olivier Alata, Alain Treméau. Joint Color-Spatial-Directional clustering and Region Merging (JCSD-RM) for unsupervised RGB-D image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, ⟨10.1109/TPAMI.2015.2513407⟩. ⟨ujm-01273670⟩