Detection and Tracking of People in a Dense Crowd through Deep Learning Approach: A Systematic Literature Review

Muhammad Firdaus Mohamed  Badauraudine; Megat Norulazmi Megat  Mohamed Noor; Mohd Shahizan  Othman; Haidawati Mohamad  Nasir

Authors

Muhammad Firdaus Mohamed Badauraudine Universiti Kuala Lumpur Malaysian Institute of Information Technology, Kuala Lumpur, Malaysia
Megat Norulazmi Megat Mohamed Noor Universiti Kuala Lumpur Malaysian Institute of Information Technology, Kuala Lumpur, Malaysia
Mohd Shahizan Othman Universiti Teknologi Malaysia, Johor Bharu, Malaysia
Haidawati Mohamad Nasir Universiti Kuala Lumpur Malaysian Institute of Information Technology, Kuala Lumpur, Malaysia

Keywords:

Localization; Dense crowd; Track; Deep learning; Re-identification; Annotation.

Abstract

Crowd-related incidents, such as the Hillsborough Disaster and the Kanjuruhan Stadium stampede, often result from poor crowd management, leading to tragedies like suffocation and crushing. To mitigate human error in crowd control, this research explores the use of deep learning for the detection and tracking of individuals in dense crowds. The study focuses on implementing artificial intelligence for automated crowd monitoring through a localization map, with an emphasis on re-identification accuracy and auto-annotation of targets in datasets. A systematic literature review (SLR) was conducted following the PRISMA guidelines, analyzing 4384 articles published between 2019 and 2024 across five databases. 13 primary studies met the inclusion criteria and were analyzed to address questions related to the accuracy of crowd tracking and detection. This SLR aims to provide insights and reference points for further research in artificial intelligence, particularly in the areas of auto annotation and re-identification for crowd monitoring.

Downloads

Download data is not yet available.

References

Li J. A systematic literature review on feature selection for machine learning-based attack classification for IoT security. Int J Sensor Networks. 2023;X(Y4):000-000.

Amosa TI, Sebastian P, Izhar LI, Ibrahim O, Ayinla LS, Bahashwan AA, et al. Multi-camera multi-object tracking: A review of current trends and future advances. Neurocomputing. 2023;552:126558. https://doi.org/10.1016/j.neucom.2023.126558

Athilakshmi R, Sainagakrishna PS, Chowdary Kota SS, Teja MC, Venkatesh T, Prasad VJ. Enhancing real-time human tracking using YOLONAS-DeepSort fusion models. 2023 7th International Conference on Electronics, Communication and Aerospace Technology (ICECA). 2023;1118-25. https://doi.org/10.1109/ICECA58529.2023.10394864

Deb T, Rahmun M, Bijoy SA, Raha MH, Khan MA. UUCT - HyMP: Towards tracking dispersed crowd groups from UAVs. 2021 International Joint Conference on Neural Networks (IJCNN). 2021;1-8. https://doi.org/10.1109/IJCNN52387.2021.9533600

Franchi G, Aldea E, Dubuisson S, Bloch I. Tracking hundreds of people in densely crowded scenes with particle filtering supervising deep convolutional neural networks. 2020 IEEE International Conference on Image Processing (ICIP). 2020;2071-75. https://doi.org/10.1109/ICIP40778.2020.9190953

Khadka AR, Oghaz MM, Matta W, Cosentino M, Remagnino P, Argyriou V. Learning how to analyse crowd behaviour using synthetic data. CASA ’19: Computer Animation and Social Agents. 2019;11-14. https://doi.org/10.1145/3328756.3328773

Li X, Yang Y, Xu Y, Wang C, Li L. Crowd abnormal behavior detection combining movement and emotion descriptors. ICNSER2020: The 2nd International Conference on Industrial Control Network and System Engineering Research. 2020;106-10. https://doi.org/10.1145/3411016.3411166

Liu D, Wang Z, Meng X. Fast intensive crowd counting model of Internet of Things based on multi-scale attention mechanism. IET Image Process. 2022;ipr2.12686. https://doi.org/10.1049/ipr2.12686

Wang X, Gao C, Xin M, Zhang S, Zhang M. Topology and channel affinity reinforced global attention for person re-identification. Int J Intell Syst. 2021;36(9):5136-60. https://doi.org/10.1002/int.22506

Wong V, Law K. Fusion of CCTV video and spatial information for automated crowd congestion monitoring in public urban spaces. Algorithms. 2023;16(3):154. https://doi.org/10.3390/a16030154

Xiang S, You G, Guan M, Chen H, Yan B, Liu T, et al. Less is more: Learning from synthetic data with fine-grained attributes for person re-identification. arXiv. 2021. https://doi.org/10.48550/ARXIV.2109.10498

Yeh KH, Hsu IC, Chou YZ, Chen GY, Tsai YS. An aerial crowd-flow analyzing system for drone under YOLOv5 and StrongSort. 2022 International Automatic Control Conference (CACS). 2022;1-6. https://doi.org/10.1109/CACS55319.2022.9969785

Zhang Y, Chen H, Bao W, Lai Z, Zhang Z, Yuan D. Handling heavy occlusion in dense crowd tracking by focusing on the heads. arXiv. 2023. https://doi.org/10.48550/ARXIV.2304.07705

Dubey SK, Satyanarayana JV, Krishna Mohan C. False positive elimination in object detection methods for videos. Proc SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 130720J (2024 April 3). https://doi.org/10.1117/12.3023362