Argos: A Decentralized Federated System for Detection of Traffic Signs in CAVs

TL;DR

This paper introduces a decentralized federated learning system for traffic sign detection in connected vehicles, addressing privacy and communication issues while demonstrating effective model accuracy improvements through various configurations.

Contribution

It proposes a novel federated learning framework tailored for vehicular traffic sign detection, including data partitioning, lightweight detectors, and evaluation of multiple aggregation algorithms in simulated environments.

Findings

Increasing server rounds improves accuracy significantly.

Moderate local epochs balance efficiency and performance.

FedProx outperforms other aggregators in handling data heterogeneity.

Abstract

Connected and automated vehicles generate vast amounts of sensor data daily, raising significant privacy and communication challenges for centralized machine learning approaches in perception tasks. This study presents a decentralized, federated learning framework tailored for traffic sign detection in vehicular networks to enable collaborative model training without sharing raw data. The framework partitioned traffic sign classes across vehicles for specialized local training using lightweight object detectors, aggregated model parameters via algorithms like FedProx, FedAdam and FedAVG in a simulated environment with the Flower framework, and evaluated multiple configurations including varying server rounds, local epochs, client participation fractions, and data distributions. Experiments demonstrated that increasing server rounds from 2 to 20 boosted accuracy from below 0.1 to over 0.8, moderate local epochs (8-10) provided optimal efficiency with accuracies around 0.67, higher client participation fractions enhanced generalization up to 0.83, FedProx outperformed other aggregators in handling heterogeneity, non-IID data distributions reduced performance compared to IID, and training duration primarily scaled with the number of rounds rather than aggregation strategy. We conclude that this federated approach may offer a scalable, privacy-preserving solution for real-world vehicular deployments, potentially guiding future integrations of robust aggregation and communication optimizations to advance intelligent transportation systems.