Abstract
In order to obtain effective crowd relationships for crowd behavior analysis, an adaptive crowd segmentation method based on coherent motion detection is proposed. This method can improve the accuracy of segmentation results and be adaptively applied to various collective scenes that have different distributions at different scales. Firstly, an orientation clustering algorithm and a spatial joint strategy are proposed to preliminarily profile all agents into several partitions with different motion orientations. Then, the Natural Nearest Neighbor algorithm is introduced to construct the adaptive crowd motion networks combining with the profiling results, which can describe the neighborhood relationships of agents with stronger coherence. Finally, the improved Coherent Neighbor Invariance optimized by fusing motion information of neighbors is proposed to segment crowds with coherent motions from the crowd motion networks. The experiment results on videos depicting real-world crowd scenes indicate that the proposed method is effective and adaptive to various scenes.
Similar content being viewed by others
References
Shao, J., Kang, K., Chen, C.L., et al. (2015). Deeply Learned Attributes for Crowded Scene Understanding. In Proceedings of IEEE International Conference on Computer Vision (pp. 4657–4666).
Jing, S., Chen, C.L., Kang, K., et al. (2017). Crowded Scene Understanding by Deeply Learned Volumetric Slices. IEEE Transactions on Circuits and Systems for Video Technology, 27(3), 613–623.
Yi, S., Li, H.S., Wang, X.G. (2015). Understanding pedestrian behaviors from stationary crowd groups. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (pp. 3488–3496).
Fradi, H., Luvison, B., Pham, Q.C. (2017). Crowd Behavior Analysis Using Local Mid-Level Visual Descriptors. IEEE Transactions on Circuits and Systems for Video Technology, 27(3), 589–602.
Rao, A.S., Gubbi, J., Marusic, S., et al. (2016). Crowd Event Detection on Optical Flow Manifolds. IEEE Transactions on Cybernetics, 46(7), 1524–1537.
Wang, J., & Xu, Z. (2016). Spatio-temporal texture modelling for real-time crowd anomaly detection. Computer Vision and Image Understanding, 144(C), 177–187.
Yu, Y., Shen, W., Huang, H., et al. (2017). Abnormal event detection in crowded scenes using two sparse dictionaries with saliency. Journal of Electronic Imaging, 26(3), 033013.
Benabbas, Y., Ihaddadene, N., Djeraba, C. (2011). Motion pattern extraction and event detection for automatic visual surveillance. EURASIP Journal on Image and Video Processing, 2011, 1–15.
Solmaz, B., Moore, B.E., Shah, M. (2012). Identify behaviours in crowd scenes using stability analysis for dynamical systems. IEEE Transaction on Pattern Analysis and Machine Intelligence, 34(10), 2064–2070.
Zhou, B.L., Tang, X.O., Wang, X.G. (2015). Learning collective crowd behaviors with dynamic pedestrian-agents. International Journal of Computer Vision, 111(1), 50–68.
Han, T.T., Yao, H.G., Sun, X.S., et al. (2016). Unsupervised discovery of crowd activities by saliency-based clustering. Neurocomputing, 171, 347–361.
Li, T., Chang, H., Wang, M., et al. (2014). Crowded scene analysis: a survey. IEEE Transactions on Circuits and Systems for Video Technology, 25(3), 367–386.
Ali, S., & Shah, M. (2007). A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. (pp. 1-6).
Mehran, R., Moore, B.E., Shah, M. (2010). A streakline representation of flow in crowded scenes. In Proceedings of European Conference on Computer Vision (pp. 439–452).
Wu, S., & San, W.H. (2012). Crowd motion partitioning in a scattered motion field. IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics, 42(5), 1443–1454.
Song, L., Jiang, F., Shi, Z., Katsaggelos, A.K. (2011). Understanding dynamic scenes by hierarchical motion pattern mining. In Proceedings of IEEE International Conference Multimedia and Expo (pp. 1–6).
Zhou, B.L., Wang, X.G., Tang, X.O. (2011). Random field topic model for semantic region analysis in crowded scenes from tracklets. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (pp. 3441–3448).
Fu, W., Wang, J., Li, Z., et al. (2012). Learning semantic motion patterns for dynamic scenes by improved sparse topical coding. In Proceedings of IEEE International Conference Multimedia and Expo (pp. 296–301).
Cheriyadat, A.M., & Radke, R.J. (2008). Detecting dominant motions in dense crowds. IEEE Journal of Selected Topics in Signal Processing, 2(4), 568–581.
Jodoin, P.M., Benezeth, Y., Wang, Y. (2013). Meta-tracking for video scene understanding. In Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance (pp. 1–6).
Zhou, B.L., Zhang, H., Wang, X.G. (2014). Measuring crowd collectiveness. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), 1586–1599.
Zhao, X., & Medioni, G. (2011). Robust unsupervised motion pattern inference from video and applications. In Proceedings of IEEE International Conference on Computer Vision (pp. 715–722).
Gnana, P., & Babu, R. (2014). Crowd flow segmentation based on motion vectors in H.264 compressed domain. In Proceedings of IEEE International Conference on Electronics, Computing and Communication Technologies (pp. 1–5).
Zhou, B.L., Tang, X.o., Wang, X.G. (2012). Coherent filtering: detecting coherent motions from crowd clutters. In Proceedings of European Conference on Computer Vision (pp. 857–871).
Zhu, F., Wang, X.G., Yu, N.H. (2014). Crowd tracking with dynamic evolution of group structures. In Proceedings of European Conference on Computer Vision (pp. 139–154).
Wang, X.G. (2014). Profiling stationary crowd groups. In Proceedings of IEEE International Conference on Multimedia and Expo (pp. 1–6).
Shandilya, S.G., & Timme, M. (2011). Inferring network topology from complex dynamics. New Journal of Physics, 13(1), 1–12.
Jiang, J., Wu, X.H., He, X.H., et al. (2015). Measuring crowd collectiveness via compressive sensing. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, 98(11), 2263–2266.
Shao, J., Loy, C.C., Wang, X.G. (2014). Scene-independent group profiling in crowd. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2227–2234).
Lin, W.Y., Mi, Y., Wang, W.Y., et al. (2016). A Diffusion and Clustering-based Approach for Finding Coherent Motions and Understanding Crowd Scenes. IEEE Transactions on Image Processing, 25(4), 1674–1687.
Baker, S., & Matthews, I. (2004). Lucas-Kanade 20 years on: a unifying framework. International Journal of Computer Vision, 56(3), 221–255.
Ozturk, O., Yamasaki, T., Aizawa, K. (2010). Detecting dominant motion flows in unstructured/structured crowd scenes. In Proceedings of International Conference on Pattern Recognition (pp. 3533–3536).
Shao, J., Dong, N., Zhao, Q. (2015). An adaptive clustering approach for group detection in the crowd. In Proceedings of IEEE International Conference on Systems, Signals and Image Processing (pp. 77–80).
Lim, M.K., Kok, V.J., Loy, C.C., Chan, C.S. (2014). Crowd saliency detection via global similarity structure. In Proceedings of International Conference on Pattern Recognition (pp. 3957–3962).
Huang, J.L., & Zhu, Q.S. (2014). A clustering algorithm based on natural nearest neighbor. Journal of Computational Information Systems, 10(13), 1–8.
Zou, X.L., Zhu, Q.S., Yang, R.L. (2011). Natural nearest neighbor for isomap algorithm without free-parameter. Advanced Materials Research, 219-220, 994–998.
Zhang, S., Mouhoub, M., Sadaoui, S. (2014). 3N-Q: natural nearest neighbor with quality. Computer and Information Science, 7(1), 94–102.
Strehl, A., & Ghosh, J. (2003). Cluster ensembles: a knowledge reuse framework for combining multiple partitions. The Journal of Machine Learning Research, 3, 583–617.
Acknowledgements
This work is funded by National Natural Science Foundation of China(NO.61701029).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fan, Z., Jiang, J., Weng, S. et al. Adaptive Crowd Segmentation Based on Coherent Motion Detection. J Sign Process Syst 90, 1651–1666 (2018). https://doi.org/10.1007/s11265-017-1309-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-017-1309-8