DOI : https://doi.org/10.18517/ijaseit.14.1.19764

Development of a Risk Space Prediction Model Based on CCTV Images Using Deep Learning: Crowd Collapse

JeongHyeon Chang (1), Hyesung Jung (2), Woongil Park (3)
(1) Contents Convergence Software Research Institute, Kyonggi University, 16227, Republic of Korea
(2) Department of Criminology, Kyonggi University , 16227, Republic of Korea
(3) Department of Criminology, Kyonggi University , 16227, Republic of Korea
Fulltext View | Download
How to cite (IJASEIT) :
Chang , JeongHyeon, et al. “Development of a Risk Space Prediction Model Based on CCTV Images Using Deep Learning: Crowd Collapse”. International Journal on Advanced Science, Engineering and Information Technology, vol. 14, no. 1, Feb. 2024, pp. 189-95, doi:10.18517/ijaseit.14.1.19764.
Citation Format :
Crowd disasters are not limited to events but can occur at any time and place where large crowds are densely gathered. The most significant factor contributing to injuries in mass gatherings is pressure. The likelihood of injuries due to pressure significantly increases when the crowd density exceeds 5-6 individuals per square meter. Once a crowd disaster occurs, it becomes challenging for rescue and medical personnel to access the affected area, potentially exacerbating the situation. However, since there is no single clear solution to address crowd disasters, there is a need for a system that can detect and analyze them in advance or in real-time. This research aims to contribute to the proactive detection and analysis of various crowd disasters, focusing on improving strategies for disaster response. In this study, we utilized a dataset of 50 videos from 35 individual incidents to propose a framework that classifies the risk levels into Crowd Crush, Crowd Wave, and Crowd Collapse. Additionally, we analyzed the feasibility of real-time detection using P2PNet (Point to Point Network), Yolo (You Only Look Once) v8, and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithms, moving away from prior still image-based detection methods. Our research outcomes provide new evidence for the feasibility of real-time detection using DBSCAN in Crowd Disaster scenarios. Moreover, the findings from this study can serve as valuable reference material for upcoming research, particularly emphasizing the algorithmic analysis of crowd collapses.

A. Sharma et al., “Global mass gathering events and deaths due to crowd surge, stampedes, crush and physical injuries – Lessons from the Seoul Halloween and other disasters,” Travel Medicine and Infectious Disease, vol. 52, p. 102524, Mar. 2023, doi:10.1016/j.tmaid.2022.102524.

C. Feliciani, A. Corbetta, M. Haghani, and K. Nishinari, “Trends in crowd accidents based on an analysis of press reports,” Safety Science, vol. 164, p. 106174, Aug. 2023, doi:10.1016/j.ssci.2023.106174.

J. J. Fruin, “Pedestrian planning and design,” in Pedestrian Planning and Design, 3rd ed., New York, NY, USA: McGraw-Hill, 1971, ch. 3, pp. 39-68.

Soon-Joo Wang, “Understanding and Approaching the Crowd Crush Incident due to Mass Crowding - Cases and Current Status -,” Korean Disastronomy Review, vol. 1, no. 1, pp. 69-80, 2023.

Ki-Wook Kim, “Developing Strategies for Preventing Multiple Dense Crowd Accidents,” Busan development forum, Vol. 198, 2022, 122-129. Available: https://kiss.kstudy.com/Detail/Ar?key=3999509.

D. Tin, L. Cheng, R. Hata, H. Shin, and G. Ciottone, “Clashes and crowds: protests, riots, and other mass gathering events in North America 2021–2022,” Public Health, vol. 221, pp. 166–169, Aug. 2023, doi: 10.1016/j.puhe.2023.06.022.

R. Park and J. Jo, “Reference Class-Based Improvement of Object Detection Accuracy,” International Journal on Advanced Science, Engineering and Information Technology, vol. 10, no. 4, pp. 1526–1535, Aug. 2020, doi: 10.18517/ijaseit.10.4.12792.

D. Helbing and P. Mukerji, “Crowd disasters as systemic failures: analysis of the Love Parade disaster,” EPJ Data Science, vol. 1, no. 1, Jun. 2012, doi: 10.1140/epjds7.

H. Liang, J. Du, and S. C. Wong, “A Continuum model for pedestrian flow with explicit consideration of crowd force and panic effects,” Transportation Research Part B: Methodological, vol. 149, pp. 100–117, Jul. 2021, doi: 10.1016/j.trb.2021.05.006.

M. Haghani and R. Lovreglio, “Data-based tools can prevent crowd crushes,” Science, vol. 378, no. 6624, pp. 1060–1061, Dec. 2022, doi:10.1126/science.adf5949.

D. Helbing, A. Johansson, and H. Z. Al-Abideen, “Dynamics of crowd disasters: An empirical study,” Physical Review E, vol. 75, no. 4, Apr. 2007, doi: 10.1103/physreve.75.046109.

A. Sieben and A. Seyfried, “Inside a life-threatening crowd: Analysis of the Love Parade disaster from the perspective of eyewitnesses,” Safety Science, vol. 166, p. 106229, Oct. 2023, doi:10.1016/j.ssci.2023.106229.

Q. Song et al., “Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Oct. 2021, doi:10.1109/iccv48922.2021.00335.

L. Yajing and D. Zhongjian, “Abnormal Behavior Detection in Crowd Scene Using YOLO and Conv-AE,” 2021 33rd Chinese Control and Decision Conference (CCDC), May 2021, doi:10.1109/ccdc52312.2021.9602095.

E. Kanjo, D. Ortega Anderez, A. Anwar, A. Al Shami, and J. William, “CrowdTracing: Overcrowding Clustering and Detection System for Social Distancing,” Jun. 2021, doi:10.36227/techrxiv.14709762.v1.

P. S. Karthika, V. Kedar, and A. Verma, “A walk accessibility-based approach to assess crowd management in mass religious gatherings,” Journal of Transport Geography, vol. 104, p. 103443, Oct. 2022, doi:10.1016/j.jtrangeo.2022.103443.

W. Shu, J. Wan, K. C. Tan, S. Kwong, and A. B. Chan, “Crowd Counting in the Frequency Domain,” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2022, doi:10.1109/cvpr52688.2022.01900.

T. R. Toha, N. A. Al-Nabhan, S. I. Salim, M. Rahaman, U. Kamal, and A. B. M. A. A. Islam, “LC-Net: Localized Counting Network for Extremely Dense Crowds,” Applied Soft Computing, vol. 123, p. 108930, Jul. 2022, doi: 10.1016/j.asoc.2022.108930.

H. Xu, X. Wang, D. Wang, B. Duan, and T. Rui, “Object detection in crowded scenes via joint prediction,” Defence Technology, vol. 21, pp. 103–115, Mar. 2023, doi:10.1016/j.dt.2021.10.007.

L. Niu, X. Wang, C. Duan, Q. Shen, and W. Liu, “Local Point Matching Network for Stabilized Crowd Counting and Localization,” Lecture Notes in Computer Science, pp. 566–579, 2022, doi:10.1007/978-3-031-18907-4_44.

Y. Hao, H. Du, M. Mao, Y. Liu, and J. Fan, “A Survey on Regression-Based Crowd Counting Techniques,” Information Technology and Control, vol. 52, no. 3, pp. 693–712, Sep. 2023, doi:10.5755/j01.itc.52.3.33701.

A.J. Azmawi, W.-N. Mohd-Isa, and A. A. A. Rahman, “Telecommunication Fiber Box Detection Using YOLO in Urban Environment,” International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 6, pp. 2136–2144, Dec. 2023, doi:10.18517/ijaseit.13.6.19027.

A. Deshpande and K. Warhade, “SADY: Student Activity Detection Using YOLO-based Deep Learning Approach,” International Journal on Advanced Science, Engineering and Information Technology, vol. 13, no. 4, pp. 1501–1509, Jul. 2023, doi:10.18517/ijaseit.13.4.18393.

P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A Review of Yolo Algorithm Developments,” Procedia Computer Science, vol. 199, pp. 1066–1073, 2022, doi:10.1016/j.procs.2022.01.135.

M. Ş. Gündüz and G. Işık, “A new YOLO-based method for real-time crowd detection from video and performance analysis of YOLO models,” Journal of Real-Time Image Processing, vol. 20, no. 1, Jan. 2023, doi:10.1007/s11554-023-01276-w.

R. P. D. Redondo, C. Garcia-Rubio, A. F. Vilas, C. Campo, and A. Rodriguez-Carrion, “A hybrid analysis of LBSN data to early detect anomalies in crowd dynamics,” Future Generation Computer Systems, vol. 109, pp. 83–94, Aug. 2020, doi:10.1016/j.future.2020.03.038.

M. Hahsler, M. Piekenbrock, and D. Doran, “dbscan: Fast Density-Based Clustering with R,” Journal of Statistical Software, vol. 91, no. 1, 2019, doi:10.18637/jss.v091.i01.

W. Alhajri, A. Templeton, and A. Moore, “Social norms and risks at mass gatherings: A systematic review,” International Journal of Disaster Risk Reduction, vol. 88, p. 103586, Apr. 2023, doi:10.1016/j.ijdrr.2023.103586.

H. Kim, H. Im, S. Lee, Y. Ju, and S. Kwon, “Establishment of Crowd Management Safety Measures Based on Crowd Density Risk Simulation,” Journal of the Korean Society of Safety, vol. 38, no. 2, pp. 96–103, Apr. 2023.

V. Karbovskii, O. Severiukhina, I. Derevitskii, D. Voloshin, A. Presbitero, and M. Lees, “The impact of different obstacles on crowd dynamics,” Journal of Computational Science, vol. 36, p. 100893, Sep. 2019, doi: 10.1016/j.jocs.2018.06.010.

H. Yamamoto, D. Yanagisawa, C. Feliciani, and K. Nishinari, “Body-rotation behavior of pedestrians for collision avoidance in passing and cross flow,” Transportation Research Part B: Methodological, vol. 122, pp. 486–510, Apr. 2019, doi: 10.1016/j.trb.2019.03.008.

K. P S and A. Verma, “Evaluating the gap choice decisions of pedestrians in conflict situations in mass religious gatherings and controlled experimental setup – A pilot study,” Journal of Choice Modelling, vol. 49, p. 100450, Dec. 2023, doi:10.1016/j.jocm.2023.100450.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).