Shots segmentation-based optimized dual-stream framework for robust human activity recognition in surveillance video

Shots segmentation-based optimized dual-stream framework for robust human activity recognition in surveillance video

Nowadays, for controlling crime, surveillance cameras are typically installed in all public places to ensure urban safety and security. However, automating Human Activity Recognition (HAR) using computer vision techniques faces several challenges such as lowlighting, complex spatiotemporal features,...

Full description

Bibliographic Details
Main Authors: Altaf Hussain, Samee Ullah Khan, Noman Khan, Waseem Ullah, Ahmed Alkhayyat, Meshal Alharbi, Sung Wook Baik
Format: Article
Language:English
Published: Elsevier 2024-03-01
Series:Alexandria Engineering Journal
Subjects:
Activity Recognition
Video Classification
Surveillance System
Lowlight Image Enhancement
Dual Stream Network
Transformer Network
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016823009936

Internet

http://www.sciencedirect.com/science/article/pii/S1110016823009936

Similar Items