Abstract
The abnormal event detection becomes an important topic recently. This paper presents a method to detect the crowd gathering, as well as the commotion event after the crowd gathering. The proposed stillness model and the motion model are based on the improved background subtraction and the optical flow feature. We construct the long-term stillness level by the break bucket model and clustering the instantaneous stillness level. Then the crowd gathering event is decided by the threshold with the long-term stillness level. Furthermore, the motion model is applied for detecting the commotion event after the crowd gathering. In the experiment, we used the dataset of PET2009. The proposed method is verified by the experiment with 97% accuracy.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-020-08827-4/MediaObjects/11042_2020_8827_Fig9_HTML.png)
Similar content being viewed by others
References
Albiol A, Albiol A, Silla J (2009) Statistical video analysis for crowds counting. In: 2009 16th IEEE international conference on image processing (ICIP), ISSN 1522-4880, pp 2569–2572
Barnich O, Van Droogenbroeck M (2011) ViBe: A universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709–1724
Chebiyyam M, Reddy RD, Dogra DP, Bhaskar H, Mihaylova L (2018) Motion anomaly detection and trajectory analysis in visual surveillance. Multim Tools Appl 77(13):16223–16248
Cheriyadat AM, Bhaduri BL, Radke RJ (2008) Detecting multiple moving objects in crowded environments with coherent motion regions. In: 2008 IEEE computer society conference on computer vision and pattern recognition workshops, ISSN 2160–7508, pp 1–8
Chondro P, Liu CY, Chen CY, Ruan SJ (2019) Detecting abnormal massive crowd flows: Characterizing fleeing en masse by analyzing the acceleration of object vectors. IEEE Consum Electron Mag 8:32–37
Farnebäck G, Bigun J, Gustavsson T (2003) Image analysis: Two-frame motion estimation based on polynomial expansion. Springer, Berlin, pp 363–370
Fradi H, Dugelay JL (2015) Towards crowd density-aware video surveillance applications. Inf Fusion 24:3–15
Fradi H, Dugelay JL (2016) Spatial and temporal variations of feature tracks for crowd behavior analysis. J Multimodal User Int 10:307–315
Gong C, Zhao YJ, Dong LQ, Yu XM, Chen P, Liu WW (2015) All-optical background subtraction readout method for bimaterial cantilever array sensing. Opt Express 23:20576–20581
Gupta T, Nunavath V, Roy S (2019) CrowdVAS-net: A deep-CNN based framework to detect abnormal crowd-motion behavior in videos for predicting crowd disaster. In: 2019 IEEE international conference on systems, Man and cybernetics (SMC), pp 2877–2882
Harrouss OE, Moujahid D, Tairi H (2015) Motion detection based on the combining of the background subtraction and spatial color information. In: 2015 Intelligent Systems and Computer Vision (ISCV), pp 1–4
Hussain N, Yatim HS Md, Hussain NL, Yan JLS, Haron F (2011) CDES: A pixel-based crowd density estimation system for Masjid al-Haram. Safety Sci 49:824–833. ISSN 0925-7535
Khan SA, Hussain S, Xiaoming S, Yang S (2018) An effective framework for driver fatigue recognition based on intelligent facial expressions analysis. IEEE Access 6(13):67459–67468
Khan SA, Ishtiaq M, Nazir M, Shaheen M (2018) Face recognition under varying expressions and illumination using particle swarm optimization. J Comput Sci 28:94–100
La Vigne NG, Lowry SS, Markman J, Dwyer A Evaluating the use of public surveillance cameras for crime control and prevention - a summary, Tech. Rep., Sep. 2011. [Online]. Available: https://www.urban.org/research/publication
Li T, Chang H, Wang M, Ni B, Hong R, Yan S (2015) Crowded scene analysis: A survey. IEEE Trans Circ Syst Vid Technol 51:367–386
Liu CY, Liao WH, Ruan SJ (2018) Crowd gathering detection based on the foreground stillness model. IEICE Trans Inf Syst E101.D(7):1968–1971
Myo T, Leng YY, Pau C, How-lung E, Paolo R (2013) Intelligent multimedia surveillance: Current trends and research: A literature review on video analytics of crowded scenes. Springer, Berlin, pp 17–36
Saleh SAM, Suandi SA, Ibrahim H (2015) Recent survey on crowd density estimation and counting for visual surveillance. Eng Appl Artif Intell 41:103–114
Suzuki S, be K (1985) Topological structural analysis of digitized binary images by border following. Comput Vis Graph Image Process 30(1):32–46
Swathi HY, Shivakumar GV, Mohana HS (2017) Crowd behavior analysis: A survey. In: 2017 international conference on recent advances in electronics and communication technology (ICRAECT), pp 169–178. https://doi.org/10.1109/ICRAECT.2017.66
Xie S, Zhang X, Cai J (2018) Video crowd detection and abnormal behavior model detection based on machine learning method. Neural Comput Appl 31:175–184
Xiong G, Cheng J, Wu X, Chen YL, Ou Y, Xu Y (2012) An energy model approach to people counting for abnormal crowd behavior detection. Neurocomputing 83:121–135
Xiong G, Wu X, Chen Y, Ou Y (2011) Abnormal crowd behavior detection based on the energy model. In: 2011 IEEE international conference on information and automation, pp 495–500
Xu Y, Lu L, Xu Z, He J, Zhou J, Zhang C (2019) Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering. Mach Vis Appl 30:945–958
Yugendar P, Ravishankar KVR (2019) Neuro-fuzzy-based crowd speed analysis at mass gathering events. Jordan J Civil Eng 13(3):446–458
Zhang Z, Li M (2012) Optical Engineering: Crowd density estimation based on statistical analysis of local intra-crowd motions for public area surveillance, vol 51
Zhao R, Liu Q, Li C, Dong D, Hu Q, Ma Y (2019) Fuzzy neural network based scenario features extraction and mapping model for crowd evacuation stability analysis. J Phys Conf Ser 77:1176
Zhao T, Nevatia R, Wu B (2008) Segmentation and tracking of multiple humans in crowded environments. IEEE Trans Pattern Anal Mach Intell 30:1198–1211
Acknowledgements
The author wishes to acknowledge the help of Prof. Derlis O. Gregor in giving helpful comments on the part of the work. We want to thank anonymous reviewers and the editor for their comments.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, DS., Liu, CY., Liao, WH. et al. Crowd gathering and commotion detection based on the stillness and motion model. Multimed Tools Appl 79, 19435–19449 (2020). https://doi.org/10.1007/s11042-020-08827-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08827-4