›› 2017,Vol. 32 ›› Issue (3): 520-535.doi: 10.1007/s11390-017-1741-z

所属专题： Artificial Intelligence and Pattern Recognition； Computer Graphics and Multimedia

• Special Section on Selected Paper from NPC 2011 • 上一篇    下一篇

基于Helmholtz-Hodge分解的运动物体场构图算法在无先验知识混合运动场分割中的应用研究

Cui-Cui Zhang1, Zhi-Lei Liu2,*, Member, CCF   

  1. 1. School of Marine Science and Technology, Tianjin University, Tianjin 300072, China;
    2. Tianjin Key Laboratory of Cognitive Computing and Application, School of Computer Science and Technology Tianjin University, Tianjin 300072, China
  • 收稿日期:2017-01-19 修回日期:2017-04-06 出版日期:2017-05-05 发布日期:2017-05-05
  • 通讯作者: Zhi-Lei Liu E-mail:zhileiliu@tju.edu.cn
  • 作者简介:Cui-Cui Zhang received her Ph.D. degree in computer science from the Kyoto University, Kyoto, in 2015. She is currently an assistant professor in the School of Marine Science and Technology, Tianjin University, Tianjin. Her research interests are computer graphics and visualization.
  • 基金资助:

    This work is supported by the National Natural Science Foundation of China under Grant No. 61503277.

Prior-Free Dependent Motion Segmentation Using Helmholtz-Hodge Decomposition Based Object-Motion Oriented Map

Cui-Cui Zhang1, Zhi-Lei Liu2,*, Member, CCF   

  1. 1. School of Marine Science and Technology, Tianjin University, Tianjin 300072, China;
    2. Tianjin Key Laboratory of Cognitive Computing and Application, School of Computer Science and Technology Tianjin University, Tianjin 300072, China
  • Received:2017-01-19 Revised:2017-04-06 Online:2017-05-05 Published:2017-05-05
  • Contact: Zhi-Lei Liu E-mail:zhileiliu@tju.edu.cn
  • About author:Cui-Cui Zhang received her Ph.D. degree in computer science from the Kyoto University, Kyoto, in 2015. She is currently an assistant professor in the School of Marine Science and Technology, Tianjin University, Tianjin. Her research interests are computer graphics and visualization.
  • Supported by:

    This work is supported by the National Natural Science Foundation of China under Grant No. 61503277.

PDF (PC)

868

在运动相机拍摄的动态场景中，由于物体的运动和相机的运动互相影响，对动态场景中的运动物体分割非常具有挑战性。运动相机补偿算法被认为是一种比较有效的解决方法，然而现有的这类算法需要利用好相机运动种类与场景结构的先验知识，但这些先验知识在很多情况下是无法获知的。此外，由于二维运动场在三维空间中会受到深度变化的影响，运动物体的分割也具有深度依赖问题。为了解决上述两个问题，本文引入基于Helmholtz-Hodge分解（HHD）的面向运动物体场的构图算法（OOM），用于无先验知识的运动物体分割。首先，本方法利用HHD通过对二维运动场（光流场）分解成无旋成分和无散度成分，可以将任意种类的相机运动用这两个成分唯一表示，从而无需关于相机运动种类的先验知识；然后，本方法利用能够将三维场景中相机的运动表示成与深度无关的部分，从而能够消除深度变化对运动物体分割的影响；最后，为了能够将运动物体从分解的光流场中有效的提取出来，本方法采用了一种时空约束的Quadtree标注算法。为了验证本方法的有效性，在多个标准数据上进行了实验，结果表明本方法对复杂场景中的运动物体分割的准确率较传统算法提高了10%-20%.

Abstract: Motion segmentation in moving camera videos is a very challenging task because of the motion dependence between the camera and moving objects. Camera motion compensation is recognized as an effective approach. However, existing work depends on prior-knowledge on the camera motion and scene structure for model selection. This is not always available in practice. Moreover, the image plane motion suffers from depth variations, which leads to depth-dependent motion segmentation in 3D scenes. To solve these problems, this paper develops a prior-free dependent motion segmentation algorithm by introducing a modified Helmholtz-Hodge decomposition (HHD) based object-motion oriented map (OOM). By decomposing the image motion (optical flow) into a curl-free and a divergence-free component, all kinds of camera-induced image motions can be represented by these two components in an invariant way. HHD identifies the camera-induced image motion as one segment irrespective of depth variations with the help of OOM. To segment object motions from the scene, we deploy a novel spatio-temporal constrained quadtree labeling. Extensive experimental results on benchmarks demonstrate that our method improves the performance of the state-of-the-art by 10%～20% even over challenging scenes with complex background.

[1] Cucchiara R, Prati A, Vezzani R. Real-time motion segmentation from moving cameras. Real-Time Imaging, 2004, 10(3): 127-143.

[2] Li H, Wu W, Wu E. Robust interactive image segmentation via graph-based manifold ranking. Computational Visual Media, 2015, 1(3): 183-195.

[3] Zhang F L, Wang J, Zhao H, Martin R R, Hu SM. Simultaneous camera path optimization and distraction removal for improving amateur video. IEEE Transactions on Image Processing, 2015, 24(12): 5982-5994.

[4] Zhang F L, Wu X, Zhang H T, Wang J, Hu S M. Robust background identification for dynamic video editing. ACM Transactions on Graphics, 2016, 35(6): 197:1-197:12.

[5] Zhang Y, Tang Y L, Cheng K L. Efficient video cutout by paint selection. Journal of Computer Science and Technology, 2015, 30(3): 467-477.

[6] Zografos V, Nordberg K. Fast and accurate motion segmentation using linear combination of views. In Proc. the 22nd British Machine Vision Conference (BMVC), Aug.29- Sept.2, 2011.

[7] Aldroubi A. A review of subspace segmentation: Problem, nonlinear approximations, and applications to motion segmentation. ISRN Signal Process, 2013, Article ID 4174492.

[8] Ichimura N. Motion segmentation based on factorization method and discriminant criterion. In Proc. the 7th IEEE International Conference on Computer Vision (ICCV), September 1999, pp.600-605.

[9] Vidal R, Ma Y, Soatto S et al. Two-view multibody structure from motion. International Journal of Computer Vision (IJCV), 2006, 68(1): 7-25.

[10] Sugaya Y, Kanatani K. Geometric structure of degeneracy for multi-body motion segmentation. In Proc. the 2nd International Workshop on Statistical Methods in Video Processing, May 2004, pp.13-25.

[11] Costeira J, Kanade T. A multibody factorization method for independently moving objects. International Journal of Computer Vision (IJCV), 1998, 29(3): 159-179.

[12] Kanatani K, Matsunaga C. Estimating the number of independent motions for multibody motion segmentation. In Proc. the 5th Asian Conference on Computer Vision, February 2002, pp.7-12.

[13] Shi F, Zhou Z, Xiao J, Wu W. Robust trajectory clustering for motion segmentation. In Proc. the IEEE International Conference on Computer Vision (ICCV), December 2013, pp.3088-3095.

[14] Ochs P, Malik J, Brox T. Segmentation of moving objects by long term video analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014, 36(6): 1187-1200.

[15] Su Y, Sun M T, Hsu V. Global motion estimation from coarsely sampled motion vector field and the applications. IEEE Transactions on Circuits System and Video Technology, 2005, 15(2): 232-242.

[16] Smolic A, Hoeynck M, Ohm J R. Low-complexity global motion estimation from P -frame motion vectors for MPEG- 7 applications. In Proc. the International Conference on Image Processing (ICIP), September 2000, pp.271-274.

[17] Chen Y M, Bajic I V. Motion vector outlier rejection cascade for global motion estimation. IEEE Signal Processing Letters, 2010, 17(2): 197-200.

[18] Fischler M, Bolles R. RANSAC random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981, 24(6): 381-395.

[19] Chen Y M, Bajic I V. A joint approach to global motion estimation and motion segmentation from a coarsely sampled motion vector field. IEEE Transactions on Circuits Systtem and Video Technology, 2011, 21(9): 1316-1328.

[20] Qian C, Baji? I V. Global motion estimation under translation-zoom ambiguity. In Proc. the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), August 2013, pp.46-51.

[21] Narayana M, Hanson A, Learned-Miller E. Coherent motion segmentation in moving camera videos using optical flow orientations. In Proc. the IEEE International Conference on Computer Vision (ICCV), December 2013, pp.1577- 1584.

[22] Tong Y, Lombeyda S, Hirani A N, Desbrun M. Discrete multiscale vector field decomposition. ACM Transactions on Graphics (TOG), 2003, 22(3): 445-452.

[23] Polthier K, Preuβ E. Identifying vector fields singularities using a discrete Hodge decomposition. In Visualization and Mathematics Ⅲ., Hege H C, Polthier K (eds.), Springer, 2003, pp.123-134.

[24] Irani M, Anandan P. A unified approach to moving object detection in 2D and 3D scenes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(6): 577- 589.

[25] Brox T, Bruhn A, Papenberg N, Weickert J. High accuracy optical flow estimation based on a theory for warping. In Proc. the 8th European Conference on Computer Vision (ECCV), May 2004, pp.25-36.

[26] von Helmholtz H. über integrale der hydrodynamischen Gleichungen, welche den wirbelbewegungen entsprechen. Journal Für Die Reine Und Angewandte Mathematik, 2010, 55(1858): 25-55. (in German)

[27] Bhatia H, Norgard G, Pascucci V, Bremer P T. The Helmholtz-Hodge Decomposition - A survey. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2013, 19(8): 1386-1404.

[28] Baker S, Scharstein D, Lewis J P, Roth S, Black M J, Szeliskiv R. A database and evaluation methodology for optical flow. International Journal of Computer Vision, 2011, 92(1): 1-31.

[29] Liang X, Zhang C, Matsuyama T. Inlier estimation for moving camera motion segmentation. In Proc. the 12th Asian Conference on Computer Vision (ACCV), November 2014, pp.352-367.

[30] Liang X, Zhang C, Matsuyama T. A general inlier estimation for moving camera motion segmentation. IPSJ Transactions on Computer Vision and Applications, 2015, 7: 163-174.

[31] Tron R, Vidal R. A benchmark for the comparison of 3-D motion segmentation algorithms. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2007.

[32] Brox T, Malik J. Object segmentation by long term analysis of point trajectories. In Proc. the 11th European Conference on Computer Vision (ECCV), September 2010, pp.282-295.

[33] Tsai D, Flagg M, Rehg J. Motion coherent tracking with multi-label MRF optimization. In Proc. the British Machine Vision Conference, Aug.31-Sept.3, 2010.

[34] Liang X, McOwan P, Johnston A. A biologically inspired framework for spatial and spectral velocity estimations. Journal of the Optical Society of America A, 2011, 28(4): 713-723.

[35] Yan J, Pollefeys M. A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In Proc. the 9th European Conference on Computer Vision (ECCV), May 2006, pp.94-106.

[36] Dembczynski K, Jachnik A, Kotlowski W, Waegeman W, Hullermeier E. Optimizing the F -measure in multi-label classification: Plug-in rule approach versus structured loss minimization. In Proc. the 30th International Conference on Machine Learning (ICML), June 2013, pp.1130-1138.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 刘明业; 洪恩宇;. Some Covering Problems and Their Solutions in Automatic Logic Synthesis Systems[J]. , 1986, 1(2): 83 -92 .
[2] 陈世华;. On the Structure of (Weak) Inverses of an (Weakly) Invertible Finite Automaton[J]. , 1986, 1(3): 92 -100 .
[3] 高庆狮; 张祥; 杨树范; 陈树清;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] 陈肇雄; 高庆狮;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[5] 黄河燕;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .
[6] 闵应骅; 韩智德;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[7] 唐同诰; 招兆铿;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] 闵应骅;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] 朱鸿;. Some Mathematical Properties of the Functional Programming Language FP[J]. , 1987, 2(3): 202 -216 .
[10] 李明慧;. CAD System of Microprogrammed Digital Systems[J]. , 1987, 2(3): 226 -235 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：