Federated Learning-based Semantic Segmentation for Lane and Object Detection in Autonomous Driving

TL;DR

A scalable, privacy-preserving FL framework tailored for AVs, optimizing communication efficiency while balancing performance and data security is offered.

Abstract

Autonomous Vehicles (AVs) require precise lane and object detection to ensure safe navigation. However, centralized deep learning (DL) approaches for semantic segmentation raise privacy and scalability challenges, particularly when handling sensitive data. This research presents a new federated learning (FL) framework that integrates secure deep Convolutional Neural Networks (CNNs) and Differential Privacy (DP) to address these issues. The core contribution of this work involves: (1) developing a new hybrid UNet-ResNet34 architecture for centralized semantic segmentation to achieve high accuracy and tackle privacy concerns due to centralized training, and (2) implementing the privacy-preserving FL model, distributed across AVs to enhance performance through secure CNNs and DP mechanisms. In the proposed FL framework, the methodology distinguishes itself from the existing approach through the following: (a) ensuring data decentralization through FL to uphold user privacy by eliminating the need for centralized data aggregation, (b) integrating DP mechanisms to secure sensitive model updates against potential adversarial inference attacks, and (c) evaluating the frameworks performance and generalizability using RGB and semantic segmentation datasets derived from the CARLA simulator. Experimental results show significant improvements in accuracy, from 81.5% to 88.7% for the RGB dataset and from 79.3% to 86.9% for the SEG dataset over 20 to 70 Communication Rounds (CRs). Global loss was reduced by over 60%, and minor accuracy trade-offs from DP were observed. This study contributes by offering a scalable, privacy-preserving FL framework tailored for AVs, optimizing communication efficiency while balancing performance and data security.

Figures (22)

• Figure 1: Overall Framework of the Proposed Research Study
• Figure 2: Phase-1 and Phase-2 Model Architectures. (A) Phase-1: Hybrid UNet-ResNet34 Framework, (B) Hybrid UNet-ResNet34 Architecture, (C) FL Workflow
• Figure 3: Examples of Images and Corresponding Segmentation Labels from the CARLA Simulator Dataset
• Figure 4: FL-based CNN Classification Model. (A) RGB Dataset, (B) SEG Dataset
• Figure 5: Comparison of Mean IoU Across Different Object Classes