Segmentation of 3D Articulated Components by Slice-Based Vertex-Weighted Reeb Graph

A fast and efficient algorithm for segmentation of the articulated components of 3D objects is proposed. The algorithm is marked by several novel features, such as DCEL-based fast orthogonal slicing, weighted Reeb graph with slice areas as vertex weights, and graph cut by exponential averaging. Each of the three sets of orthogonal slices obtained from the object is represented by a vertex-weighted Reeb graph of low complexity, as the slicing is done with an appropriate grid resolution. Each linear subgraph in a Reeb graph is traversed from its leaf node up to an articulation node or up to a node whose weight exceeds a dynamically-set threshold, based on exponential averaging of the predecessor weights in the concerned subgraph. The nodes visited in each linear subgraph are marked by a unique component number, thereby helping the inverse mapping for marking the articulated regions during final segmentation. Theoretical analysis shows that the algorithm runs faster for objects with smaller surface area and for larger grid resolutions. The algorithm is stable, invariant to rotation, and leads to natural segmentation, as evidenced by experimentation with a varied dataset.

[1]  Ning Zhu,et al.  Graph-Based Optimization with Tubularity Markov Tree for 3D Vessel Segmentation , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Joseph H. Nurre,et al.  Locating landmarks on human body scan data , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[3]  T. Funkhouser,et al.  Randomized cuts for 3D mesh analysis , 2008, SIGGRAPH 2008.

[4]  Daniel Cohen-Or,et al.  Consistent mesh partitioning and skeletonisation using the shape diameter function , 2008, The Visual Computer.

[5]  Naoufel Werghi,et al.  A discrete Reeb graph approach for the segmentation of human body scans , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[6]  Naoufel Werghi,et al.  A robust approach for constructing a graph representation of articulated and tubular-like objects from 3D scattered data , 2006, Pattern Recognit. Lett..

[7]  Guillaume Damiand,et al.  First Results for 3D Image Segmentation with Topological Map , 2008, DGCI.

[8]  Ioannis Pratikakis,et al.  3D articulated object retrieval using a graph-based representation , 2010, The Visual Computer.

[9]  Partha Bhowmick,et al.  Fast Slicing of Orthogonal Covers Using DCEL , 2012, IWCIA.

[10]  Deepu Rajan,et al.  Salient Object Detection through Over-Segmentation , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[11]  Ross T. Whitaker,et al.  Partitioning 3D Surface Meshes Using Watershed Segmentation , 1999, IEEE Trans. Vis. Comput. Graph..

[12]  Luiz Velho,et al.  A Hierarchical Segmentation of Articulated Bodies , 2008, Comput. Graph. Forum.

[13]  Marco Attene,et al.  Mesh Segmentation - A Comparative Study , 2006, IEEE International Conference on Shape Modeling and Applications 2006 (SMI'06).

[14]  Alberto Del Bimbo,et al.  3D Mesh decomposition using Reeb graphs , 2009, Image Vis. Comput..

[15]  Konrad Polthier,et al.  Combinatorial Image Analysis , 2014, Lecture Notes in Computer Science.

[16]  Thomas Funkhouser,et al.  A benchmark for 3D mesh segmentation , 2009, SIGGRAPH 2009.

[17]  Jacques-Olivier Lachaud,et al.  Multi-Label Simple Points Definition for 3D Images Digital Deformable Model , 2009, DGCI.

[18]  Bernard Chazelle,et al.  Strategies for Polyhedral Surface Decomposition: an Experimental Study , 1997, Comput. Geom..

[19]  Ayellet Tal,et al.  Mesh segmentation using feature point and core extraction , 2005, The Visual Computer.

[20]  Xiangyang Ju,et al.  Automatic segmentation of 3D human body scans , 2000 .