Application of Integral Optical Flow for Determining Crowd Movement from Video Images Obtained Using Video Surveillance Systems
Study of crowd movement is an important practical problem, and its solution is used in video surveillance systems for preventing various emergency situations. In the general case, a group of fast-moving people is of more interest than a group of stationary or slow-moving people. We propose a new method for crowd movement analysis using a video sequence, based on integral optical flow. We have determined several characteristics of a moving crowd such as density, speed, direction of motion, symmetry, and in/out index. These characteristics are used for further analysis of a video scene.
Keywordsintegral optical flow motion analysis crowd movement
Unable to display preview. Download preview PDF.
- 2.J. Shao, C. Loy, K. Kang, and X. Wang, in: Proc. IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 5629–5628.Google Scholar
- 3.R. Mehran, A. Oyama, and M. Shah, in: Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009), pp. 935–942.Google Scholar
- 4.S. Ali and M. Shah, in: Proc. IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 1–6.Google Scholar
- 6.A. Niranjil Kumar and C. Sureshkumar, Int. J. Adv. Res. Comput. Commun. Eng., 3, No. 9, 7935–7939 (2014).Google Scholar
- 7.Shipra Ojha and S. R. Sakhare, Int. J. Sci. Eng. Res., 6, No. 6, 1119–1123 (2015).Google Scholar
- 8.N. A. Sjarif, S. M. Shamsuddin, and S. Z. Hashim, Int. J. Adv. Software Comput. Appl., 4, No. 1, 1–33 (2012).Google Scholar
- 10.G. Farnebäck, in: Scandinavian Conference on Image Analysis (2003), pp. 363–370.Google Scholar
- 11.C. Chen, S. Ye, H. Chen, O. V. Nedzvedz, and S. V. Ablameyko, Zh. Prikl. Spektrosk., 84, No. 1, 138–146 (2017) [C. Chen, S. Ye, H. Chen, O. Nedzvedz, and S. Ablameyko, J. Appl. Spectrosc., 84, No. 1, 120–128 (2017) (English translation)].Google Scholar
- 12.P. Allain, N. Courty, and T. Corpetti, in: Proc. First ICPR International Workshop on Pattern Recognition and Crowd Analysis, November 2012 (2012), pp. 1–6.Google Scholar