Abstract
Crowd behavior analysis is a hot research topic in the field of computer vision. This paper proposes a salient region detection method based on weighted networks approach in crowded scenes. Firstly, crowd velocity field is calculated from video sequences by using Pyramid Lucas-Kanade optical flow algorithm. Secondly, every velocity vector for each point in the 2D velocity field is regarded as a node, and the included angle of two velocity vectors is calculated by a vector dot product formula. After that an angle threshold is set to judge whether there is an edge between these two nodes. Finally, the connection degree between nodes is evaluated by the numerical value of the included angle. The node degree strength can reflect the number of edges and the edge strength between nodes. In this context, the salient regions refer to the areas with high node degree strength in relation to the dominant crowded scenes. In the experiments, several different scenarios are used to evaluate the performance of the proposed method, and the results show that the proposed method can detect salient regions in crowded scenes effectively.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Challenger, R., Clegg, C.W., Robinson, M.A.: Understanding crowd behaviours: supporting evidence. In: Leigh, M. (ed.): Understanding Crowd Behaviours (Crown, 2009), pp. 1–326 (2009)
Lim, M.K., Kok, V.J., Loy, C.C., Chan, C.S.: Crowd saliency detection via global similarity structure. In: International Conference on Pattern Recognition, pp. 3957–3962, August 2014
Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In: IEEE Conference Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)
Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. In: IEEE Conference Computer Vision and Pattern Recognition, pp. 2376–2383 (2010)
Boiman, O., Irani, M.: Detecting irregularities in images and in video. Int. J. Comput. Vis. 74(1), 17–31 (2007)
Hung, H.S.W.: From visual saliency to video behavior understanding, Ph.D. thesis, University of London (2007)
Loy, C., Xiang, T., Gong, S.: Salient motion detection in crowded scenes. In: ISCCSP, Rome, Italy, pp. 1–4, May 2012
Lim, M.K., Chan, C.S., Monekosso, D., Remagnino, P.: Detection of salient regions in crowded scenes. Electron. Lett. 50(5), 363–365 (2014)
Chen, G., Wang, X., Li, X.: Introduction to Complex Networks: Models, Structures and Dynamics. Higher Education Press, Beijing (2012)
Johnson, J.L., Padgett, M.L.: Pcnn models and applications. IEEE Trans. Neural Netw. 10(3), 480–498 (1998)
Wu, Z., Lu, X., Deng, Y.: Image edge detection based on local dimension: a complex networks approach. Physica Statis. Mech. Appl. 440, 9–18 (2015)
Bouguet, J.Y.: Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm. Opencv Documents 22(2), 363–381 (1999)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence, pp. 674–679. Morgan Kaufmann Publishers Inc. (1981)
Scientific collaboration networks. I. Network construction and fundamental results. Physical Review E Statistical Nonlinear & Soft Matter Physics, 64(1 Pt 2), 016131 (2001)
Boccaletti, S., Latora, V., Moreno, Y., et al.: Complex networks: structure and dynamics. Phys. Rep. 424(4–5), 175–308 (2006)
Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 935–942 (2009)
Ali, S., Shah, M.: A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. In: CVPR, Minneapolis, MN, USA, pp. 1–6, June 2007
Acknowledgments
This research is supported by National Natural Science Foundation of China (No. 61771418, 61271409).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zheng, J., Zhang, X. (2018). Detection of Salient Regions in Crowded Scenes Based on Weighted Networks Approach. In: Satoh, S. (eds) Image and Video Technology. PSIVT 2017. Lecture Notes in Computer Science(), vol 10799. Springer, Cham. https://doi.org/10.1007/978-3-319-92753-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-92753-4_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92752-7
Online ISBN: 978-3-319-92753-4
eBook Packages: Computer ScienceComputer Science (R0)