Motion pattern-based scene classification using adaptive synthetic oversampling and fully connected deep neural network

MS Mohammed, A Al-Dhamari, W Saeed… - IEEE …, 2023 - ieeexplore.ieee.org
Analyzing crowded environments has become an increasingly researched topic in computer
vision community, largely due to its myriad practical applications, including enhanced video …

[PDF][PDF] Visual Motion Segmentation in Crowd Videos Based on Spatial-Angular Stacked Sparse Autoencoders.

A Hafeezallah, A Al-Dhamari… - … Systems Science & …, 2023 - cdn.techscience.cn
Visual motion segmentation (VMS) is an important and key part of many intelligent crowd
systems. It can be used to figure out the flow behavior through a crowd and to spot unusual …

Label noise robust crowd counting with loss filtering factor

Z Xu, H Lin, Y Chen, Y Li - Applied Artificial Intelligence, 2024 - Taylor & Francis
Crowd counting, a crucial computer vision task, aims at estimating the number of individuals
in various environments. Each person in crowd counting datasets is typically annotated by a …

Motion segmentation using Ward's hierarchical agglomerative clustering for crowd disaster risk mitigation

A Hafeezallah, A Al-Dhamari… - International Journal of …, 2024 - Elsevier
Motion segmentation has gained increasing attention due to its significance for many public
surveillance applications, such as behavior understanding and density estimation. Thus …

Training a Regression-Based Model for Crowd Counting in Transit Cars Using Ranked Image Pairs and Triplets

H Lee, K Lee, J Kang, K Sohn - IEEE Access, 2024 - ieeexplore.ieee.org
Accurately measuring the level of crowding in transit cars is crucial for ensuring passenger
safety and efficient operation. However, applying object detection algorithms to crowd …