Exploring Personalized Federated Learning Architectures for Violence Detection in Surveillance Videos
By: Mohammad Kassir, Siba Haidar, Antoun Yaacoub
Potential Business Impact:
Finds trouble in city cameras better.
The challenge of detecting violent incidents in urban surveillance systems is compounded by the voluminous and diverse nature of video data. This paper presents a targeted approach using Personalized Federated Learning (PFL) to address these issues, specifically employing the Federated Learning with Personalization Layers method within the Flower framework. Our methodology adapts learning models to the unique data characteristics of each surveillance node, effectively managing the heterogeneous and non-IID nature of surveillance video data. Through rigorous experiments conducted on balanced and imbalanced datasets, our PFL models demonstrated enhanced accuracy and efficiency, achieving up to 99.3% accuracy. This study underscores the potential of PFL to significantly improve the scalability and effectiveness of surveillance systems, offering a robust, privacy-preserving solution for violence detection in complex urban environments.
Similar Papers
Advancing Personalized Federated Learning: Integrative Approaches with AI for Enhanced Privacy and Customization
Machine Learning (CS)
Makes AI smarter without sharing your private data.
Federated Learning for Video Violence Detection: Complementary Roles of Lightweight CNNs and Vision-Language Models for Energy-Efficient Use
CV and Pattern Recognition
Makes cameras detect violence using less power.
Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning
Machine Learning (CS)
Makes AI models easier to trick with hidden bad data.