iccv iccv2013 iccv2013-263 iccv2013-263-reference knowledge-graph by maker-knowledge-mining

263 iccv-2013-Measuring Flow Complexity in Videos


Source: pdf

Author: Saad Ali

Abstract: In this paper a notion of flow complexity that measures the amount of interaction among objects is introduced and an approach to compute it directly from a video sequence is proposed. The approach employs particle trajectories as the input representation of motion and maps it into a ‘braid’ based representation. The mapping is based on the observation that 2D trajectories of particles take the form of a braid in space-time due to the intermingling among particles over time. As a result of this mapping, the problem of estimating the flow complexity from particle trajectories becomes the problem of estimating braid complexity, which in turn can be computed by measuring the topological entropy of a braid. For this purpose recently developed mathematical tools from braid theory are employed which allow rapid computation of topological entropy of braids. The approach is evaluated on a dataset consisting of open source videos depicting variations in terms of types of moving objects, scene layout, camera view angle, motion patterns, and object densities. The results show that the proposed approach is able to quantify the complexity of the flow, and at the same time provides useful insights about the sources of the complexity.


reference text

[1] Chen-Yu Chen et. al, Motion Entropy Feature and its Applications to Event-based Segmentation of Sports Video, EURASIP J. Adv. Signal Process, 2008. 2

[2] Y. F. Ma, and H. J. Zhang, A New Perceived Motion-based Shot Content Representation, IEEE ICIP, 2001. 2

[3] S. Suthaharan et. al, Perceptually Tuned Video Watermarking Scheme Using Motion Entropy Masking, IEEE Region 10th Conference and Exhibition, vol. 1, 1999. 2

[4] K. A. Peker, A. Divakaran, T. V. Papathomas, Automatic Measurement of Intensity of Motion Activity of Video Segments, Proc. SPIE Storage and Retrieval for Media Databases, 2001. 2

[5] S. Jeannin and A. Divakaran, MPEG-7 Visual Motion Descriptors, IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, pp. 720-724, 2001. 2

[6] T. Liu et al., A Novel Video Keyframe Extraction Algorithm based on Perceived Motion Energy Model, IEEE Transactions on Circuits and Systems for Video Technology, 13(10), 2003. 2

[7] G. Iyengar, and A. Lippman, VideoBook: An Experiment in Characterization of Video, IEEE ICIP, 1996. 2

[8] J.-L Thiffeault, Braids of Entangled Particle Trajectories, Chaos: 4A,n 5 ,In 6terdisciplinary Journal of Nonlinear Science, 20(1), 2010. 2,

[9] M. R. Allshouse and J.-L. Thiffeault, Detecting Coherent Structures Using Braids, Physica D, 241(2), 2012. 4, 5

[10] J. G. Puckett et al., Trajectory Entanglement in Dense Granular Materials, Journal of Statistical Mechanics: Theory and Experiment, 2012. 6

[11] J. O. Moussafir, On Computing the Entropy of Braids, Func. Anal. and Other Math., 1(1), 37-46, 2006. 2, 6

[12] I. A. Dynnikov, On a Yang-Baxter Map and the Dhornoy Ordering, Russian Math Survey, 57, 592-594, 2002. 5

[13] S. M. Cox and M. D. Finn, Two Dimensional Stokes Flow Driven by Elliptical Paddles, Physics of Fluids, 19(1 1), 2007. 6

[14] Thomas Brox and J. Malik, Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation, IEEE Trans. on PAMI, 33(3), 2011. 1

[15] Saad Ali and Mubarak Shah, Floor Fields for Tracking in High Density Crowd Scenes, In ECCV 2008. 1, 2

[16] Louis Kratz and Ko Nishino, Tracking Pedestrians Using Local Spatio-Temporal Motion Patterns in Extremely Crowded Scenes, IEEE Trans. on PAMI, 34(5), 2012. 1

[17] B. Zhou et al., Understanding Collective Crowd Behaviors: Learning a Mixture Model of Dynamic Pedestrian-Agents, In IEEE CVPR, 2012. 1, 2

[18] L. Xu et al., Motion Detail Preserving Optical Flow Estimation, IEEE Trans. on PAMI, 2012. 1, 3

[19] J. Yan et al., A General Framework for Motion Segmentation: Independent, Articulated, Rigid, Non-rigid, Degenerate and Nondegenerate, In ECCV, 2006. 1

[20] N. Vasconcelos and A. Lippman, Empirical Bayesian Motion Segmentation, IEEE Trans. on PAMI, 23(2), 2001. 1

[21] Thomas Brox and J. Malik, Object Segmentation by Long Analysis of Point Trajectories, In ECCV, 2010. 1

[22] I. Saleemi et al., Scene Understanding by Statistical Modeling of Motion Patterns, In IEEE CVPR, 2010. 1

[23] D. Lin et al., Modeling and Estimating Persistent Motion with Geometric Flows, In IEEE CVPR, 2010. 1, 2

[24] Saad Ali and Mubarak Shah, A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis, In IEEE CVPR, 2007. 2, 3

[25] B. E. Moore et al., Visual Crowd Surveillance through a Hydrodynamics Lens, In Commun. ACM, 54(12), 2011. 3

[26] T. Brox et al.,High Accuracy Optical Flow Estimation based on a Theory for Warping, In ECCV 2004. 3 11 110044