Skip to main content

High-level feature extraction for crowd behaviour analysis: a computer vision approach.

Bruno, A., Ferjani, M., Sabeur, Z., Arbab-Zavar, B., Cetinkaya, D., Johnstone, L., Sallal, M. and Benaouda, D., 2021. High-level feature extraction for crowd behaviour analysis: a computer vision approach. In: ICIAP 2021: International Conference on Image Analysis and Processing: Human Behaviour Analysis for Smart City Environment Safety (HBAxSCES), 23-27 May 2021, Lecce, Italy, 1-12.

Full text available as:

PDF (Conference Workshop Paper)
HBAxSCES1_paper_6.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


Official URL:


The advent of deep learning has brought in disruptive techniques with unprecedented accuracy rates in so many fields and scenarios. Tasks such as the detection of regions of interest and semantic features out of images and video sequences are quite effectively tackled because of the availability of publicly available and adequately annotated datasets. This paper describes a use case scenario with a deep learning models’ stack being used for crowd behaviour analysis. It consists of two main modules preceded by a pre-processing step. The first deep learning module relies on the integration of YOLOv5 and DeepSORT to detect and track down pedestrians from CCTV cameras’ video sequences. The second module ingests each pedestrian’s spatial coordinates, velocity, and trajectories to cluster groups of people using the Coherent Neighbor Invariance technique. The method envisages the acquisition of video sequences from cameras overlooking pedestrian areas, such as public parks or squares, in order to check out any possible unusualness in crowd behaviour. Due to its design, the system first checks whether some anomalies are underway at the microscale level. Secondly, It returns clusters of people at the mesoscale level depending on velocity and trajectories. This work is part of the physical behaviour detection module developed for the S4AllCities H2020 project.

Item Type:Conference or Workshop Item (Paper)
Additional Information:Funded by S4AllCities: Smart Spaces Safety and Security for All Cities. Best Paper Award in the HBAxSCES Workshop.
Uncontrolled Keywords:Crowd Behaviour; Computer Vision; Artificial Intelligence; Deep Learning
Group:Faculty of Science & Technology
ID Code:37092
Deposited By: Symplectic RT2
Deposited On:24 Jun 2022 10:56
Last Modified:24 Jun 2022 12:33


Downloads per month over past year

More statistics for this item...
Repository Staff Only -