iccv iccv2013 iccv2013-21 iccv2013-21-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Chang Ma, Zhongqian Dong, Tingting Jiang, Yizhou Wang, Wen Gao
Abstract: In thispaper, wepropose a novelperception-based shape decomposition method which aims to decompose a shape into semantically meaningful parts. In addition to three popular perception rules (the Minima rule, the Short-cut rule and the Convexity rule) in shape decomposition, we propose a new rule named part-similarity rule to encourage consistent partition of similar parts. The problem is formulated as a quadratically constrained quadratic program (QCQP) problem and is solved by a trust-region method. Experiment results on MPEG-7 dataset show that we can get a more consistent shape decomposition with human perception compared with other state-of-the-art methods both qualitatively and quantitatively. Finally, we show the advantage of semantic parts over non-meaningful parts in object detection on the ETHZ dataset.
[1] J. Aleotti and S. Caselli. A 3D shape segmentation approach for robot grasping by parts. Robotics and Autonomous Systems, 60(3):358–366, 2012.
[2] D. H. Ballard. Generalizing the Hough transform to detect arbitrary shapes. Pattern Recognition, 13(2): 111–122, 1981 .
[3] R. H. Byrd, J. C. Gilbert, and J. Nocedal. A trust region method based on interior point techniques for nonlinear 887799 SReamndanomticp a rt0. 8B.38o69t1/0le.08s.95 0 .3G521i9r7a/0f .3e5s45970 .874M023u/0 g.s786 840 .79S50w89/a0 n.s7950980 .76M8634e/a0 n.86096 Table 3. Comparison of detection rates at 0.3/0.4 FPPI using different part templates. Objects in the apple logo divided components so it is hard to generate their random parts, we do not use this category in the experiment. category include two MNCD PSD Ours Humans Figure 10. Comparison results of ours with MNCD [17], PSD [9], and human. By considering the part-similarity and pruning the redundant cuts, our decompositions are more visually consistent with human perception.
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13] programming. Mathematical Programming, 89(1): 149–185, 2000. H. Doraiswamy and V. Natarajan. Output-sensitive construction of reeb graphs. Visualization and Computer Graphics, 18(1): 146–159, 2012. V. Ferrari, F. Jurie, and C. Schmid. From images to shape models for object detection. IJCV, 87(3):284–303, 2010. V. Ferrari, T. Tuytelaars, and L. Van Gool. Object detection by contour segment networks. In ECCV, pages 14–28. Springer, 2006. R. Gopalan, P. Turaga, and R. Chellappa. Articulationinvariant representation of non-planar shapes. In ECCV, pages 286–299. Springer, 2010. D. D. Hoffman and W. Richards. Parts of recognition. Cognition, 18:65–96, 1984. T. Jiang, Z. Dong, C. Ma, and Y. Wang. Toward perceptionbased shape decomposition. In ACCV 2012, pages 188–201 . Springer, 2013. G. Kim and E. P. Xing. On multiple foreground cosegmentation. In CVPR, pages 837–844. IEEE, 2012. L. J. Latecki and R. Lak a¨mper. Convexity rule for shape decomposition based on discrete contour evolution. CVIU, 73(3):441–454, 1999. L. J. Latecki, R. Lakamper, and T. Eckhardt. Shape descriptors for non-rigid shapes with a single closed contour. In CVPR, volume 1, pages 424–429. IEEE, 2000. J.-M. Lien and N. M. Amato. Approximate convex decomposition of polygons. In Proceedings of the twentieth annual
[14]
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22] symposium on Computational geometry, pages 17–26. ACM, 2004. H. Liu, W. Liu, and L. J. Latecki. Convex shape decomposition. In CVPR, pages 97–104. IEEE, 2010. T. Ma and L. J. Latecki. From partial shape matching through local deformation to robust global shape similarity for object detection. In CVPR, pages 1441–1448. IEEE, 2011. D. R. Martin, C. C. Fowlkes, and J. Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues. PAMI, 26(5):530–549, 2004. Z. Ren, J. Yuan, C. Li, and W. Liu. Minimum near-convex decomposition for robust shape representation. In ICCV, pages 303–310. IEEE, 2011. W. Shen, X. Bai, R. Hu, H. Wang, and L. Jan Latecki. Skeleton growing and pruning with bending potential ratio. Pattern Recognition, 44(2): 196–209, 2011. K. Siddiqi, K. J. Tresness, and B. B. Kimia. Parts of visual form: Psychophysical aspects. Perception, 25:399–424, 1996. M. Singh, G. D. Seyranian, and D. D. Hoffman. Parsing silhouettes: The short-cut rule. Perception & Psychophysics, 61(4):636–660, 1999. L. L. Walker and J. Malik. Can convexity explain how humans segment objects into parts? Journal of Vision, 3(9):503–503, 2003. L. Zhu, Y. Chen, A. Torralba, W. Freeman, and A. Yuille. Part and appearance sharing: Recursive compositional models for multi-view. In CVPR, pages 1919–1926. IEEE, 2010. 888800