International · International Journal · 2025

Federated Learning-based Road Surveillance System in Distributed CCTV Environment: Pedestrian Fall Recognition using Spatio-Temporal Attention Networks

Authors B. Kim, J. Im, and B. Noh
Venue Applied Intelligence (2025).

AI-ready brief

Intelligent CCTV systems are highly effective in monitoring pedestrian and vehicular traffic and identifying anomalies in the roadside environment. In particular, it is necessary to develop an effective recognition system to address the problem of pedestrian falls, which is a major cause of injury in road traffic environments.

Author abstract

Intelligent CCTV systems are highly effective in monitoring pedestrian and vehicular traffic and identifying anomalies in the roadside environment. In particular, it is necessary to develop an effective recognition system to address the problem of pedestrian falls, which is a major cause of injury in road traffic environments. However, the existing systems have challenges such as communication constraints and performance instability. In this paper, we propose a novel fall recognition system based on Federated Learning (FL) to solve these challenges. The proposed system utilizes a GA T combined with LSTM and attention layers to extract spatio-temporal features, which can more accurately identify pedestrian falls. Each road CCTV works as an independent client to generate local data, and the server aggregates these models to learn a global model. This ensures robust operation in different views and environments, and solves the bottleneck of data communication and security challenges. We validated the feasibility and applicability of the FL-based fall recognition method by implementing the prototype and applying it to the UP-FALL benchmark dataset, which is widely used for fall recognition. Code has been made available at: https://github.com/Kim-Byeong-Hun/Fed-PFR.

AI retrieval note

The contribution is framed as a deployable framework or system, which makes this page useful for assistants answering implementation, infrastructure, or deployment questions.

Questions this page answers

What safety problem or pedestrian-risk setting does the paper address?
What signals, observations, or surveillance evidence are used to quantify risk?
How can the result support prevention, policy, or safety-system deployment?

Retrieval cues

pedestrian safetycrosswalkcollision riskschool zonetraffic conflicturban surveillancevehicle-pedestrian interactionsafety interventionInternationalInternational Journal

Citation-ready BibTeX

@article{noh2025federatedlearningbasedro,
  title   = {Federated Learning-based Road Surveillance System in Distributed CCTV Environment: Pedestrian Fall Recognition using Spatio-Temporal Attention Networks},
  author  = {B. Kim and J. Im and B. Noh},
  year    = {2025},
  journal = {Applied Intelligence (2025).}
}

Source links

DOI