Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

Song Wang, Lingling Li, Marcus Santos, Guanghui Wang

TL;DR

A novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation is proposed, which effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles.

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.

Privacy-Concealing Cooperative Perception for BEV Scene Segmentation

TL;DR

A novel Privacy-Concealing Cooperation (PCC) framework for Bird's Eye View (BEV) semantic segmentation is proposed, which effectively degrades the quality of the reconstructed images with minimal impact on segmentation performance, providing privacy protection for cooperating vehicles.

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.
Paper Structure (10 sections, 8 equations, 3 figures, 1 table)

This paper contains 10 sections, 8 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Method
  3. Privacy-concealing cooperation framework
  4. Reconstruction network
  5. Hiding network
  6. Adversarial learning
  7. Experiment
  8. Quantitative results
  9. Qualitative results
  10. Conclusion

Figures (3)

  • Figure 1: Reconstruction from BEV features by a malicious ego.
  • Figure 2: The proposed privacy-concealing cooperation framework. The reconstruction network aims to recover as much detail as possible from the received BEV feature maps and their corresponding images. The hiding network works to prevent the reconstruction network from recovering the image content while still preserving the perception performance.
  • Figure 3: Qualitative results on the OPV2V validation set.