Browse > Article
http://dx.doi.org/10.9717/kmms.2016.19.3.531

Semantic Segmentation of Indoor Scenes Using Depth Superpixel  

Kim, Seon-Keol (Dept of media Engineering, Catholic University of Korea)
Kang, Hang-Bong (Dept of media Engineering, Catholic University of Korea)
Publication Information
Journal of Korea Multimedia Society / v.19, no.3, 2016 , pp. 531-538 More about this Journal
Abstract
In this paper, we propose a novel post-processing method of semantic segmentation from indoor scenes with RGBD inputs. For accurate segmentation, various post-processing methods such as superpixel from color edges or Conditional Random Field (CRF) method considering neighborhood connectivity have been used, but these methods are not efficient due to high complexity and computational cost. To solve this problem, we maximize the efficiency of post processing by using depth superpixel extracted from disparity image to handle object silhouette. Our experimental results show reasonable performances compared to previous methods in the post processing of semantic segmentation.
Keywords
Depth; Superpixel; RGBD; Segmentation; Semantic Segmentation;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 C. Hazirbas, J. Diebold, and D. Cremers, "Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation," Journal of Scale Space and Variational Methods in Computer Vision, 2015. Vol. 9087, pp 243-255
2 C. Couprie, C. Farabet, L. Najman, and Y. LeCun, "Indoor Semantic Segmentation Using Depth Information," International Conference on Learning Representations, 2013, 1301.3572.
3 A. Hermans, G. Floros, and B. Leibe, "Dense 3D Semantic Mapping of Indoor Scenes from RGB-D Images," Proceeding of International Conference on Robotics and Automation, 2014. 2631-2638.
4 A. Sharma, O. Tuzel, and D.W. Jacobs, "Deep Hierarchical Parsing for Semantic Segmentation," The IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 530-538
5 N. Silberman and R. Fergus, "Indoor Scene Segmentation Using a Structured Light Sensor," Proceeding of International Conference on Computer Vision Workshop on 3D Representation and Recognition, 2011, pp. 601-608.
6 J. Shotton, J.M. Winn, C. Rother, and A. Criminisi, “TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context,” International Journal of Computer Vision, Vol. 81, No. 1, pp. 2-23, 2009.   DOI
7 N. Silberman, D. Hoiem, P. Kohli, and R. Fergus, "Indoor Segmentation and Support Inference from RGBD Images," Proceeding of European Conference on Computer Vision, 2012, pp. 746-760
8 A. Krizhevsky, I. Sutskever, G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Journal of Neural Information Processing Systems, 2012, pp. 1106-1114
9 X. Ren, L. Bo, and D. Fox, ""RGB-(D) Scene Labeling: Features and Algorithms," The IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2759-2766.
10 P. Kr¨ahenb¨uhl and V. Koltun, “Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials,” Journal of Neural Information Processing Systems, 2011, pp. 109-117.
11 J. Yang, Z. Gan, X. Gui, K. Li, and C. Hou, "3-D Geometry Enhanced Super Pixels for RGB-D Data," Proceeding of Advances in Multimedia Information Processing, pp. 35-46, 2013,
12 J. Yang, Z. Gan, K. Li, and C. Hou, “Graph-based Segmentation for RGB-D Data Using 3-D Geometry Enhanced Super Pixels,” IEEE Transactions on Cybernetics, Vol. 45, No. 5, pp. 927-940.   DOI
13 R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, SLIC Superpixels, Ecole Polytechnique Federale De Lausanne Technical Report No. 149300, 2010.
14 R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, "SLIC Superpixels Compared to State of the art Superpixel Methods," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 11, pp. 2274-2282, 2012.   DOI
15 H. Peng, F. Long, and C. Ding. "Feature Selection Based on Mutual Information Criteria of Max-dependency, Max-relevance, and Min-rebundancy," Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 8, pp. 1226-1238, 2005.   DOI
16 A.L. Dani, D. Lischinski, and Y. Weiss. "Colorization Using Optimization," ACM Transactions on Graphics, Vol. 23, No. 3, pp. 689-694, 2004.   DOI
17 Y.J. Oh, H.B. Kang, " Edge Preserving using HOG Guide Filter for Image Segmentation" Jounal of Korea Multimedia Society, Vol. 18, No. 10, 2015. 10, 1164-1171   DOI