Motion Pattern-Based Scene Classification Using Adaptive Synthetic Oversampling and Fully Connected Deep Neural Network

Motion Pattern-Based Scene Classification Using Adaptive Synthetic Oversampling and Fully Connected Deep Neural Network

Analyzing crowded environments has become an increasingly researched topic in computer vision community, largely due to its myriad practical applications, including enhanced video surveillance systems and the estimation of crowd density in specific settings. This paper presents a comprehensive metho...

Full description

Bibliographic Details
Main Authors: Mohammed Sultan Mohammed, Ahlam Al-Dhamari, Waddah Saeed, Fatima N. Al-Aswadi, Sami Abdulla Mohsen Saleh, M. N. Marsono
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Computer vision
crowd analysis
collective behavior
cross-validation
ADASYN
SMOTE
Online Access:https://ieeexplore.ieee.org/document/10295438/

Internet

https://ieeexplore.ieee.org/document/10295438/

Similar Items