Abstract
Crowd density is an essential parameter of crowd dynamics that can be used to manage the crowd, predict pedestrian movement patterns, and minimize crowd risk situations. Inadequate crowd control measures in a mass gathering can eventually lead to crowd disaster. A potential solution to avoid the risk is to predict high-density crowds and prevent them before they turn fatal. Bombay Dharamshala in Ujjain is one such crowded place, where pilgrims usually choose to halt during Kumbh Mela—the world’s largest mass religious gathering. For this study, CCTV footage of Bombay Dharamshala collected on 8-May-2016 during Kumbh Mela is used. The motive of this study is to assess the performance of a deep-learning-based Image Processing Module (IPM) combined with a denoising filter in estimating pedestrian density in the video footage of a highly heterogeneous crowd. The pedestrian count as predicted by the IPM is fed into the denoising filter for noise reduction. The model used for detecting pedestrians is unique, accounting for the crowd’s heterogeneity to benefit Indian mass gathering scenarios. The combined Pedestrian Count Model (PCM) shows an accuracy of 87.28%.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Government decreases death toll in cambodian stampede (2010). http://edition.cnn.com/2010/WORLD/asiapcf/11/25/cambodia.festival.deaths/index.html
Gambrell J (2015) Saudi crush was deadliest hajj tragedy ever
Panic erupts during champions league viewing in Italy, injuring 1500 (2017). https://bnonews.com/index.php/2017/06/panic-erupts-during-champions-league-viewing-in-italy-injuring-1500/
Illiyas F, Mani S, Pradeepkumar A, Mohan K (2013) Human stampedes during religious festivals: a comparative review of mass gathering emergencies in India. Int J Disaster Risk Reduct 5:10–18. https://doi.org/10.1016/j.ijdrr.2013.09.003
Gayathri H, Aparna P, Verma A (2017) A review of studies on understanding crowd dynamics in the context of crowd safety in mass religious gatherings. Int J Disaster Risk Reduct. https://doi.org/10.1016/j.ijdrr.2017.07.017
Helbing D (1997) Verkehrsdynamik. Springer
Kormanova A (2013) A review on macroscopic pedestrian flow modelling. Acta Inform Prag 2(2):39–50
Burstedde C, Klauck K, Schadschneider A, Zittartz J (2001) Simulation of pedestrian dynamics using a two-dimensional cellular automaton. Phys A Stat Mech Appl 295:507525. https://doi.org/10.1016/S0378-4371(01)00141-8
Helbing D, Farkas I, Vicsek T (2000) Simulating dynamic features of escape panic. Nature 407:487490. https://doi.org/10.1038/35035023
Helbing D, Johansson A, Al-Abideen HZ (2007) Dynamics of crowd disasters: an empirical study. Phys Rev E, statistical, nonlinear, and soft matter physics 75:046109. https://doi.org/10.1103/PhysRevE.75.046109
Oberhagemann D, Konnecke R, Schneider V (2014) Effect of social groups on crowd dynamics: empirical findings and numerical simulations. Springer, Cham, pp 12511258. https://doi.org/10.1007/978-3-319-02447-9_103
Hou YL, Pang G (2010) Human detection in crowded scenes. In: 2010 IEEE international conference on image processing, pp 721–724. https://doi.org/10.1109/ICIP.2010.5651982
Brostow GJ, Cipolla R (2006) Unsupervised bayesian detection of independent motion in crowds. In: Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR 06), vol 1. New York, USA, pp 594–601. https://doi.org/10.1109/CVPR.2006.320
Loy CC, Gong S, Xiang T (2013) From semi-supervised to transfer counting of crowds. In: Proceedings of the 2013 IEEE International Conference on Computer Vision, ICCV 13. Sydney, Australia , pp 2256–2263. https://doi.org/10.1109/ICCV.2013.270
Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images. In: Proceedings of the 2013 IEEE conference on computer vision and pattern recognition (CVPR13). Portland, USA, pp 2547–2554. https://doi.org/10.1109/CVPR.2013.329
Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the international conference on computer vision, ICCV 99, vol 2. Washington, USA. http://dl.acm.org/citation.cfm?id=850924.851523
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR05), vol 1. San Diego, USA, pp 886–893. https://doi.org/10.1109/CVPR.2005.177
Ojala T, Pietikainen M, Maenpaa T (2000) Gray scale and rotation invariant texture classification with local binary patterns. In: Lecture notes in computer science, vol 1842, pp 404–420. https://doi.org/10.1007/3-540-45054-8_27
Bourdev L, Maji S, Malik J (2011) Describing people: a poselet-based approach to attribute classification. In: Proceedings of the 2011 international conference on computer vision, ICCV 11. Barcelona, Spain, pp 1543–1550. https://doi.org/10.1109/ICCV.2011.6126413
Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, Lecun Y (2013) Overfeat: integrated recognition, localization and detection using convolutional networks. In: International conference on learning representations (ICLR) (Banff). https://arxiv.org/abs/1312.6229
Yao H, Han K, Wan W, Hou L (2017) Deep spatial regression model for image crowd counting. CoRR abs/1710.09757. http://arxiv.org/abs/1710.09757
Shang C, Ai H, Bai B (2016) End-to-end crowd counting via joint learning local and global count. In: 2016 IEEE international conference on image processing proceedings. Phoenix, USA, pp 1215–1219. https://doi.org/10.1109/ICIP.2016.7532551
Zhang Y, Zhou D, Chen S, Gao S, Ma YS (2016) Single-image crowd counting via multi-column convolutional neural network. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). Las Vegas, USA, pp 589–597. https://doi.org/10.1109/CVPR.2016.70
Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. In: The IEEE conference on computer vision and pattern recognition (CVPR). Boston, USA. https://doi.org/10.1109/CVPR.2015.7298684
Boominathan L, Kruthiventi SSS, Babu RV (2016) Crowdnet: a deep convolutional network for dense crowd counting. In: Proceedings of the 24th ACM international conference on multimedia, MM 16. New York, USA, pp 640–644. https://doi.org/10.1145/2964284.2967300
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR. https://arxiv.org/abs/1409.1556
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Patt Anal Mach Intell 39. https://doi.org/10.1109/TPAMI.2016.257703
Kalman RE (1960) A new approach to linear filtering and prediction problems. J Basic Eng 82:35–45. https://doi.org/10.1115/1.3662552
Welch G, Bishop G (1995) An introduction to the kalman filter
Julier S, Uhlmann J (1999) A new extension of the kalman filter to nonlinear systems. Proc. SPIE 3068. https://doi.org/10.1117/12.280797
Kumar SV (2017) Traffic flow prediction using kalman filtering technique. In: Procedia engineering, vol 187. Vilnius, Lithuania, pp 582–587. https://doi.org/10.1016/j.proeng.2017.04.417
Acknowledgements
The work reported in this paper is part of the project titled “The Kumbh Mela Experiment: Measuring and Understanding the Dynamics of Mankind’s largest crowd,” funded by the Ministry of Electronics and IT, Government of India (MITO-0105); Netherlands Organization for Scientific Research, NWO (Project no. 629.002.202); and Robert Bosch Center for Cyber-Physical Systems, Indian Institute of Science, Bangalore (Grant No. RBCO001). The authors also express their gratitude toward the Kumbh Mela administration and government of Madhya Pradesh, India, for providing constant support and official permissions to carry out research work and establish an Indo-Dutch collaboration research camp at Kumbh Mela 2016.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Choubey, N., Prajapati, A.K., Verma, A., Chakraborty, A. (2021). Density Estimation of Heterogeneous Crowd in Mass Religious Gatherings Using Image Processing and Denoising Filter. In: Tiwari, A., Ahuja, K., Yadav, A., Bansal, J.C., Deep, K., Nagar, A.K. (eds) Soft Computing for Problem Solving. Advances in Intelligent Systems and Computing, vol 1393. Springer, Singapore. https://doi.org/10.1007/978-981-16-2712-5_36
Download citation
DOI: https://doi.org/10.1007/978-981-16-2712-5_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2711-8
Online ISBN: 978-981-16-2712-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)