FLAMe: Federated Learning with Attention Mechanism using Spatio-Temporal Keypoint Transformers for Pedestrian Fall Detection in Smart Cities

TL;DR

This paper introduces FLAMe, a federated learning system with attention mechanisms and spatio-temporal keypoint transformers, achieving high accuracy in pedestrian fall detection while reducing communication costs in smart city environments.

Contribution

The paper presents a novel federated learning approach with attention and keypoint transformers for fall detection, improving efficiency and privacy in smart city applications.

Findings

Achieved 94.02% accuracy in fall detection.

Reduced communication costs by about 40%.

Maintained performance comparable to centralized models.

Abstract

In smart cities, detecting pedestrian falls is a major challenge to ensure the safety and quality of life of citizens. In this study, we propose a novel fall detection system using FLAMe (Federated Learning with Attention Mechanism), a federated learning (FL) based algorithm. FLAMe trains around important keypoint information and only transmits the trained important weights to the server, reducing communication costs and preserving data privacy. Furthermore, the lightweight keypoint transformer model is integrated into the FL framework to effectively learn spatio-temporal features. We validated the experiment using 22,672 video samples from the "Fall Accident Risk Behavior Video-Sensor Pair data" dataset from AI-Hub. As a result of the experiment, the FLAMe-based system achieved an accuracy of 94.02% with about 190,000 transmission parameters, maintaining performance similar to that of existing centralized learning while maximizing efficiency by reducing communication costs by about 40% compared to the existing FL algorithm, FedAvg. Therefore, the FLAMe algorithm has demonstrated that it provides robust performance in the distributed environment of smart cities and is a practical and effective solution for public safety.