Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

TL;DR

This paper introduces a privacy-preserving cooperative perception framework for autonomous vehicles that conceals sensitive visual information in shared BEV features while maintaining high segmentation accuracy.

Contribution

It proposes a novel hiding network with adversarial training to protect visual privacy in BEV scene segmentation without sacrificing performance.

Findings

Effective concealment of visual clues in shared features.

Minimal impact on segmentation accuracy.

Enhanced privacy protection in cooperative perception.

Abstract

Cooperative perception systems for autonomous driving aim to overcome the limited perception range of a single vehicle by communicating with adjacent agents to share sensing information. While this improves perception performance, these systems also face a significant privacy-leakage issue, as sensitive visual content can potentially be reconstructed from the shared data. In this paper, we propose a novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation. Based on commonly shared BEV features, we design a hiding network to prevent an image reconstruction network from recovering the input images from the shared features. An adversarial learning mechanism is employed to train the network, where the hiding network works to conceal the visual clues in the BEV features while the reconstruction network attempts to uncover these clues. To maintain segmentation performance, the perception network is integrated with the hiding network and optimized end-to-end. The experimental results demonstrate that the proposed PCC framework effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles. The source code will be made publicly available upon publication.