Abstract
Probabilistic topic modelings, such as latent Dirichlet allocation (LDA) and correlated topic models (CTM), have recently emerged as powerful statistical tools for processing video content. They share an important property, i.e., using a common set of topics to model all data. However, such property can be too restrictive for modeling complex visual data such as crowd scenes where multiple fields of heterogeneous data jointly provide rich information about objects and events. This paper proposes graph-based extensions of LDA and CTM, referred to as GLDA and GCTM, to learn and analyze motion patterns by trajectory clustering in a highly cluttered and crowded environment. Unlike previous works that relied on a scene prior, we apply a spatio-temporal graph to uncover the spatial and temporal coherence between the trajectories of crowd motion during the learning process. The presented models advance the conventional approaches by integrating a manifold-based clustering as initialization and iterative statistical inference as optimization. The output of GLDA and GCTM are mid-level features that represent the motion patterns used later to generate trajectory clusters. Experiments on three different datasets show the effectiveness of the approaches in trajectory clustering and crowd motion modeling.
Similar content being viewed by others
References
Alghamdi, M., Gotoh, Y.: Graph-based correlated topic model for motion patterns analysis in crowded scenes from tracklets. In: The British Machine Vision Conference (BMVC) (2018)
Alghamdi, M., Gotoh, Y.: Graph-based correlated topic model for trajectory clustering in crowded videos. In: The IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1029–1037 (2018)
Ali, S., Shah, M.: Floor fields for tracking in high density crowd scenes. In: ECCV, pp. 1–14 (2008)
Ali, Y., Zafar, B., Simsim, M.: Estimation of density levels in the holy mosque from a network of cameras. In: Traffic and Granular Flow, pp. 27–34 (2016)
Blei, D., Lafferty, J.: A correlated topic model of science. Ann. Appl. Stat. 1, 17–35 (2007)
Blei, D., Ng, A., Jordan, M.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Borg, I., Groenen, P.: Modern Multidimensional Scaling: Theory and Applications. Springer, Berlin (2005)
Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: Pajdla, T., Matas, J. (eds.) Computer Vision—ECCV, pp. 25–36. Springer, Berlin (2004)
Burceanu, E., Leordeanu, M.: Learning a robust society of tracking parts using co-occurrence constraints. In: Leal-Taixé, L., Roth, S. (eds.) Computer Vision—ECCV Workshops, pp. 162–178. Springer International Publishing, Cham (2019)
Chen, M., Wang, Q., Li, X.: Patch-based topic model for group detection. Sci. China Inf. Sci. 60(11), 113101–113107 (2017)
Gariel, M., Srivastava, A.N., Feron, E.: Trajectory clustering and an application to airspace monitoring. IEEE Trans. Intell. Transp. Syst. 12(4), 1511–1524 (2011)
Kratz, L., Nishino, K.: Tracking pedestrians using local spatio-temporal motion patterns in extremely crowded scenes. IEEE Trans. PAMI 34(5), 987–1002 (2012)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: The IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol. 2, pp. 2169–2178 (2006)
Leal-Taixé, L., Milan, A., Schindler, K., Cremers, D., Reid, I.D., Roth, S.: Tracking the trackers: an analysis of the state of the art in multiple object tracking. arXiv:1704.02781 (2017)
Lee, S., Baker, J., Song, J., Wetherbe, J.: An empirical comparison of four text mining methods. In: Proceedings of the Annual Hawaii International Conference on System Sciences, pp. 1–10 (2010)
Lin, W., Mi, Y., Wang, W., Wu, J., Wang, J., Mei, T.: A diffusion and clustering-based approach for finding coherent motions and understanding crowd scenes. IEEE Trans. Image Process. 25(4), 1674–1687 (2016)
Lu, W., Wei, X., Xing, W., Liu, W.: Trajectory-based motion pattern analysis of crowds. Neurocomputing 247, 213–223 (2017)
Luo, W., Xing, J., Zhang, X., Zhao, X., Kim, T.: Multiple object tracking: a literature review. In: CoRR (2014)
Mao, Y., Zhong, H., Qi, H., Ping, P., Li, X.: An adaptive trajectory clustering method based on grid and density in mobile pattern analysis. In: Sensors (2017)
Moberts, B., Vilanova, A., van Wijk, J.: Evaluation of fiber clustering methods for diffusion tensor imaging. In: IEEE Visualization, pp. 65–72 (2005)
Pellegrini, S., Ess, A., Schindler, K., van Gool, L.: You’ll never walk alone: Modeling social behavior for multi-target tracking. In: The IEEE 12th International Conference on Computer Vision, pp. 261–268 (2009)
Rabiee, H., Mousavi, H., Nabi, M., Ravanbakhsh, M.: Detection and localization of crowd behavior using a novel tracklet-based model. Int. J. Mach. Learn. Cybernet. 9(12), 1999–2010 (2018)
Raghavendra, R., Del Bue, A., Cristani, M., Murino, V.: Abnormal crowd behavior detection by social force optimization. In: Salah, A.A., Lepri, B. (eds) Human Behavior Understanding, pp. 134–145 (2011)
Rodriguez, M., Ali, S., Kanade, T.: Tracking in unstructured crowded scenes. In: ICCV, pp. 1389–1396 (2009)
Rodriguez, M., Sivic, J., Laptev, I., Audibert, J.Y.: Data-driven crowd analysis in videos. In: The International Conference on Computer Vision (ICCV), pp. 1235–1242 (2011)
Salti, S., Cavallaro, A., Di Stefano, L.: Adaptive appearance modeling for video tracking: survey and evaluation. IEEE Trans. Image Process. 21(10), 4334–4348 (2012)
Serre, T., Wolf, L., Poggio, T.: Object recognition with features inspired by visual cortex. In: CVPR, pp. 994–1000 (2005)
Sharma, R., Guha, T.: A trajectory clustering approach to crowd flow segmentation in videos. In: ICIP, pp. 1200–1204 (2016)
Silva, V.D., Tenenbaum, J.B.: Global versus local methods in nonlinear dimensionality reduction. In: Becker, S., Thrun, S., Obermayer, K. (eds.) Advances in Neural Information Processing Systems, vol. 15, pp. 721–728. MIT Press, Cambridge (2003)
Smeulders, A.W.M., Chu, D.M., Cucchiara, R., Calderara, S., Dehghan, A., Shah, M.: Visual tracking: an experimental survey. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1442–1468 (2014)
Tomasi, C., Kanade, T.: Detection and tracking of point features. In: Technical Reports. Carnegie Mellon University (1991)
van der Maaten, L., Postma, E., van den Herik, H.: Dimensionality reduction: a comparative review. J. Mach. Learn. Res. 10, 66–71 (2009)
Vedaldi, A., Fulkerson, B.: Vlfeat: an open and portable library of computer vision algorithms. In: International Conference on Multimedia, pp. 1469–1472 (2010)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR, pp. 3360–3367 (2010)
Xu, H., Zhou, Y., Lin, W., Zha, H.: Unsupervised trajectory clustering via adaptive multi-kernel-based shrinkage. In: The IEEE International Conference on Computer Vision (ICCV) pp. 4328–4336 (2015)
Yuan, G., Xia, S., Zhang, L., Zhou, Y., Ji, C.: An efficient trajectory-clustering algorithm based on an index tree. Trans. Inst. Meas. Control 34, 850–861 (2012)
Zhou, B., Tang, X., Zhang, H., Wang, X.: Measuring crowd collectiveness. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1586–1599 (2014)
Zhou, B., Wang, X., Tang, X.: Random field topic model for semantic region analysis in crowded scenes from tracklets. In: CVPR, pp. 3441–3448 (2011)
Zou, J., Ye, Q., Cui, Y., Doermann, D., Jiao, J.: A belief based correlated topic model for trajectory clustering in crowded video scenes. In: ICPR, pp. 2543–2548 (2014)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Al Ghamdi, M., Gotoh, Y. Graph-based topic models for trajectory clustering in crowd videos. Machine Vision and Applications 31, 39 (2020). https://doi.org/10.1007/s00138-020-01092-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00138-020-01092-3