Region Segmentation based on Gaussian Dirichlet Process Mixture Model and its Application to 3D Geometric Stricture Detection
In general, image-based 3D scenes can now be found in many popular vision systems, computer games and virtual reality tours. So, It is important to segment ROI (region of interest) from input scenes as a preprocessing step for geometric stricture detection in 3D scene. In this paper, we propose a method for segmenting ROI based on tensor voting and Dirichlet process mixture model. In particular, to estimate geometric structure information for 3D scene from a single outdoor image, we apply the tensor voting and Dirichlet process mixture model to a image segmentation. The tensor voting is used based on the fact that homogeneous region in an image are usually close together on a smooth region and therefore the tokens corresponding to centers of these regions have high saliency values. The proposed approach is a novel nonparametric Bayesian segmentation method using Gaussian Dirichlet process mixture model to automatically segment various natural scenes. Finally, our method can label regions of the input image into coarse categories: “ground", “sky", and “vertical" for 3D application. The experimental results show that our method successfully segments coarse regions in many complex natural scene images for 3D.
Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1333022Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1595
 Criminisi, A., Reid, I., and Zisserman, A.: single view metrology, International Journal of Computer Vision, 40, 123-148, 2000.
 Singhal, A., Luo, J., and Zhu, W.: Probabilistic spatial context models for scene content understanding, In Computer Vision and Pattern Recognition, 235-241, 2003.
 Zhang, L., Dugas-Phocion, G., Samson, J., and Seitz, S.: Single view modeling of free-form scenes. In Computer Vision and Pattern Recognition, 990-997, 2001.
 Ziegler, R., Matusik, W., Pfister, H., and McMillan, L., 3D reconstruction using labeled image region, In Eurographics Symposium on Geometry Processing, 248-259, 2003.
 Hosea, S.P., Ranichandra, S., and Rajagopal, T.K.P.: Color Image Segmentation, International Journal of Scientific & Engineering Research, 2(3), 1-3(2011).
 Sujaritha, M. and Annadurai, S.: Color Image Segmentation using Adaptive Spatial Gaussian mixture Model, Inter. Jour. Of Information and Communication Engineering, 6(1), 28-32 (2010).
 Blackwell, D., MacQueen, J.: Ferguson distribution via Polya-urn schemes. Annals of Statistics, 1, 353--355(1973).
 Sethuraman, J.: A constructive definition of Dirichlet priors. Statistica Sinica, 4, 639--650(1994).
 The, Y.W., Jordan, M.I., Beal, M.J., and Blei, D.M.: Hierarchical Dirichlet Processes. Journal of the American Statistical Association, 101, 1566--1581(2007).
 Beal, M.J.: Varitional Algorithms for Approximate Bayesian Inference. Thesis of Doctor of Philosophy, University of London, 2003.
 Blei, D. M., Jordan, M. I.: Variational Inference for Dirichlet Process Mixtures. Bayesian Analysis, 1(1), 121-144( 2006)
 Chatzis, S. P., Tsechpenakis, G.: The infinite Hidden Markov random Field Model. IEEE Trans. on Neural Networks, 21(6), 1004-1014(2010).
 Hoiem, D., Alexei, A. E., and Martial H., Automatic photo pop-up, ACM Siggraph, 2005.