Abstract
In this paper we present a novel method for dominant motion analysis in crowded scenes, based on corner features. In our method, we initialize corner features on the scene, and advect them through optical flow. Approximating the moving corner features to individuals, their interaction forces, represented as endothermic reactions in a thermodynamic system, are computed using the enthalpy measure, thus obtaining the potential corner features of interest. These features are exploited to extract the orientation patterns, used as input priors for training a random forest. The experimental evaluation is conducted on a set of benchmark video sequences, commonly used for crowd motion analysis, and the obtained results are compared against other state of the art techniques.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Montgomery, M.: The urban transformation of the developing world. Science 319(5864), 761–764 (2008)
Basharat, A., Gritai, A., Shah, M.: Learning object motion patterns for anomaly detection and improved object detection. In: International Conference on Computer Vision and Pattern Recognition. IEEE CVPR, pp. 1–8 (2008)
Ullah, H., Tenuti, L., Conci, N.: Gaussian mixtures for anomaly detection in crowded scenes. In: IS&T/SPIE Electronic Imaging, pp. 866303. International Society for Optics and Photonics (2013)
Zhang, T., Lu, H., Li, S.: Learning semantic scene models by object classification and trajectory clustering. In: International Conference on Computer Vision and Pattern Recognition. IEEE CVPR, pp. 1940–1947 (2009)
Ullah, H., Ullah, M., Conci, N.: Real-time anomaly detection in dense crowded scenes. In: IS&T/SPIE Electronic Imaging. International Society for Optics and Photonics (2014)
Zhong, H., Shi, J., Visontai, M.: Detecting unusual activity in video. In: International Conference on Computer Vision and Pattern Recognition, IEEE CVPR, p. II–819 (2004)
Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: International Conference on Computer Vision and Pattern Recognition, IEEE CVPR, pp. 1446–1453 (2009)
Laptev, I.: On space-time interest points. International Journal of Computer Vision, IJCV 64(2-3), 107–123 (2005)
Arslan, B., Zai, Y., Shah, M.: Content based video matching using spatiotemporal volumes. Internation Journal of Computer Vision and Image Understanding, CVIU 110(3), 360–377 (2008)
Andrade, E., Blunsden, S., Fisher, R.: Modelling crowd scenes for event detection. In: International Conference on Pattern Recognition, IEEE ICPR, pp. 175–178 (2006)
Jacques, J., Musse, S., Jung, C.: Crowd analysis using computer vision techniques. IEEE Signal Processing Magazine 27(5), 66–77 (2010)
Zhan, B., Monekosso, D., Remagnino, P., Velastin, S., Xu, L.: Crowd analysis: a survey. Machine Vision and Applications 19(5), 345–357 (2008)
Qiu, F., Hu, X.: Modeling group structures in pedestrian crowd simulation. Simulation Modelling Practice and Theory 18(2), 190–205 (2010)
Rota, P., Ullah, H., Conci, N., Sebe, N.: Particles cross-influence for entity grouping. In: Proceedings of the Signal Processing Conference, IEEE EUSIPCO (2013)
Ozturk, O., Yamasaki, T., Aizawa, K.: Detecting dominant motion flows in unstructured/structured crowd scenes. In: International Conference on Pattern Recognition, IEEE ICPR, pp. 3533–3536 (2010)
Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: Advances in Neural Information Processing Systems, NIPS, pp. 1601–1608 (2004)
Chen, W., Zhao, Y., Xie, W., Sang, N.: An improved sift algorithm for image feature-matching. In: International Conference on Multimedia Technology, IEEE ICMT, pp. 197–200 (2011)
Wu, J., Cui, Z., Sheng, V.S., Zhao, P., Su, D., Gong, S.: A comparative study of sift and its variants. Measurement Science Review 13(3), 122–131 (2013)
Nadler, B., Galun, M.: Fundamental limitations of spectral clustering. In: Advances in Neural Information Processing Systems, pp. 1017–1024 (2006)
Ullah, H., Conci, N.: Crowd motion segmentation and anomaly detection via multi-label optimization. In: ICPR Workshop on Pattern Recognition and Crowd Analysis (2012)
Ullah, H., Conci, N.: Structured learning for crowd motion segmentation. In: International Conference on Image Processing, IEEE ICIP (2013)
Boykov, Y., Vekser, O., Zabi, R.: Fast approximate energy minimization via graph cuts. IEEE PAMI Transactions on Pattern Analysis and Machine Intelligence 23(11), 1222–1239 (2001)
Brunner, G., Chittajallu, D.R., Kurkure, U., Kakadiaris, I.A.: Patch-cuts: A graph-based image segmentation method using patch features and spatial relations. In: British Machine Vision Conference, BMVC (2010)
Yves, B.: Pyramidal implementation of the lucas-kanade feature tracker. Microsoft Res. Labs, Tech. Rep. (1999)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: International Conference on Computer Vision and Pattern Recognition, IEEE CVPR, pp. 1–6 (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ullah, H., Ullah, M., Conci, N. (2014). Dominant Motion Analysis in Regular and Irregular Crowd Scenes. In: Park, H.S., Salah, A.A., Lee, Y.J., Morency, LP., Sheikh, Y., Cucchiara, R. (eds) Human Behavior Understanding. HBU 2014. Lecture Notes in Computer Science, vol 8749. Springer, Cham. https://doi.org/10.1007/978-3-319-11839-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-11839-0_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11838-3
Online ISBN: 978-3-319-11839-0
eBook Packages: Computer ScienceComputer Science (R0)