Estimation of crowd density by clustering motion cues

详细信息    查看全文

• 作者：Aravinda S. Rao ; Jayavardhana Gubbi ; Slaven Marusic…
• 关键词：Video surveillance ; Crowd ; Density estimation ; People counting ; Crowd monitoring ; Optical flow ; Clustering
• 刊名：The Visual Computer
• 出版年：2015
• 出版时间：November 2015
• 年：2015
• 卷：31
• 期：11
• 页码：1533-1552
• 全文大小：2,726 KB
• 参考文献：1.Acampora, G., Loia, V., Percannella, G., Vento, M.: Trainable estimators for indirect people counting: a comparative study. In: 2011 IEEE International Conference on Fuzzy Systems (FUZZ), pp. 139-45. IEEE (2011)
  2.Aggarwal, J.K., Cai, Q., Liao, W., Sabata, B.: Articulated and elastic non-rigid motion: a review. In: Proceedings of the 1994 IEEE Workshop on Motion of Non-Rigid and Articulated Objects, pp. 2-4. IEEE (1994)
  3.Aijun, S., Mao, L., Jianfeng, L.: Real-time crowd massing risk supervision system based on massing crowd counting in public venue. In: 2009 International Symposium on Computer Network and Multimedia Technology (CNMT 2009), pp. 1-. IEEE (2009)
  4.Albiol, A., Silla, M.J., Albiol, A., Mossi, J.M.: Video analysis using corner motion statistics. In: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, pp. 31-8. IEEE (2009)
  5.Anandan, P.: A computational framework and an algorithm for the measurement of visual motion. Int. J. Comput. Vis. 2(3), 283-10 (1989). doi:10.-007/?BF00158167 CrossRef
  6.Aurich, V., Weule, J.: Non-linear gaussian filters performing edge preserving diffusion. In: Sagerer, G., Posch, S., Kummert, F. (eds.) Mustererkennung 1995. Informatik aktuell, pp. 538-45. Springer, Berlin, Heidelberg (1995)
  7.Barnich, O., Van Droogenbroeck, M.: Vibe: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709-724 (2011)MathSciNet CrossRef
  8.Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. Int. J. Comput. Vis. 12(1), 43-7 (1994)CrossRef
  9.Batur, A.U., Hayes, M.H.: Adaptive active appearance models. IEEE Trans. Image Process. 14(11), 1707-721 (2005)CrossRef
  10.Bhaskar, H., Mihaylova, L., Maskell, S.: Articulated human body parts detection based on cluster background subtraction and foreground matching. Neurocomputing 100, 58-3 (2013)CrossRef
  11.Bo, W., Nevatia, R.: Tracking of multiple, partially occluded humans based on static body part detection. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 951-58. IEEE (2006)
  12.Chan, A., Liang, Z.S., Vasconcelos, N.: Privacy preserving crowd monitoring: counting people without people models or tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1-. IEEE (2008). doi:10.-109/?CVPR.-008.-587569
  13.Chan, A., Vasconcelos, N.: Pedestrian traffic database. http://?www.?svcl.?ucsd.?edu/?projects/?peoplecnt/-/span> (2008). Accessed 22 July 2013
  14.Chan, A.B., Vasconcelos, N.: Counting people with low-level features and bayesian regression. IEEE Trans. Image Process. 21(4), 2160-177 (2012). doi:10.-109/?tip.-011.-172800 MathSciNet CrossRef
  15.Clark, A., Green, R., Grant, R.: Perspective correction for improved visual registration using natural features. In: 23rd International Conference Image and Vision Computing New Zealand (IVCNZ 2008), pp. 1-. IEEE (2008)
  16.Conde, C., Moctezuma, D., Martn De Diego, I., Cabello, E.: Hogg: gabor and hog-based human detection for surveillance in non-controlled environments. Neurocomputing 100, 19-0 (2013)CrossRef
  17.Conte, D., Foggia, P., Percannella, G., Tufano, F., Vento, M.: A method for counting people in crowded scenes. In: 2010 Seventh IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 225-32. IEEE (2010)
  18.Da Xu, R.Y., Kemp, M.: Multiple curvature based approach to human upper body parts detection with connected ellipse model fine-tuning. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 2577-580. IEEE (2009)
  19.DiCarlo, J.J., Zoccolan, D., Rust, N.C.: How does the brain solve visual object recognition? Neuron 73(3), 415-34 (2012)CrossRef
  20.Duc Thanh, N., Wanqing, L., Ogunbona, P.: A part-based template matching method for multi-view human detection. In: 24th International Conference Image and Vision Computing New Zealand (IVCNZ -9), pp. 357-62. IEEE (2009)
  21.Elgammal, A., Harwood, D., Davis, L.: Non-parametric model for background subtraction. In: Vernon, D. (ed.) Computer Vision—ECCV 2000. Lecture Notes in Computer Science, vol. 1843, pp. 751-67. Springer, Berlin (2000)
  22.Ferryman, J.: PETS 2009 Benchmark data. http://?www.?cvg.?rdg.?ac.?uk/?PETS2009/?a.?html (2009)
  23.Fleet, D., Jepson, A.: Computation of component image velocity from local phase information. Int. J. Comput. Vis. 5(1), 77-04 (1990)CrossRef
  24.Gavrila, D.M.: A bayesian, exemplar-based approach to hierarchical shape matching. IEEE Trans. Pattern Anal. Mach. Intell. 29(8), 1408-421 (2007)CrossRef
  25.Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice Hall, Inc., Upper Saddle River (2006)
  26.Grimson, W.E.L., Stauffer, C., Romano, R., Lee, L.: Using adaptive tracking to classify and monitor activities in a site. In: Proceedings of the IEEE Computer Society Co
• 作者单位：Aravinda S. Rao (1)
  Jayavardhana Gubbi (1)
  Slaven Marusic (1)
  Marimuthu Palaniswami (1)
  
  1. ISSNIP, Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, VIC, 3010, Australia
  
• 刊物类别：Computer Science
• 刊物主题：Computer Graphics
  Computer Science, general
  Artificial Intelligence and Robotics
  Image Processing and Computer Vision
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1432-2315

文摘

Understanding crowd behavior using automated video analytics is a relevant research problem in recent times due to complex challenges in monitoring large gatherings. From an automated video surveillance perspective, estimation of crowd density in particular regions of the video scene is an indispensable tool in understanding crowd behavior. Crowd density estimation provides the measure of number of people in a given region at a specified time. While most of the existing computer vision methods use supervised training to arrive at density estimates, we propose an approach to estimate crowd density using motion cues and hierarchical clustering. The proposed method incorporates optical flow for motion estimation, contour analysis for crowd silhouette detection, and clustering to derive the crowd density. The proposed approach has been tested on a dataset collected at the Melbourne Cricket Ground (MCG) and two publicly available crowd datasets—Performance Evaluation of Tracking and Surveillance (PETS) 2009 and University of California, San Diego (UCSD) Pedestrian Traffic Database—with different crowd densities (medium- to high-density crowds) and in varied environmental conditions (in the presence of partial occlusions). We show that the proposed approach results in accurate estimates of crowd density. While the maximum mean error of \(3.62\) was received for MCG and PETS datasets, it was \(2.66\) for UCSD dataset. The proposed approach delivered superior performance in \(50~\%\) of the cases on PETS \(2009\) dataset when compared with existing methods. Keywords Video surveillance Crowd Density estimation People counting Crowd monitoring Optical flow Clustering