License Plate Privacy in Collaborative Visual Analysis of Traffic Scenes

TL;DR

This paper introduces a privacy-preserving system for traffic scene analysis that protects license plate information by selectively compressing features in a multi-task model, demonstrated on the Cityscapes dataset.

Contribution

It proposes a novel multi-task model with selective feature compression to preserve license plate privacy during traffic scene analysis.

Findings

Effective privacy preservation demonstrated on Cityscapes dataset

Model maintains analysis accuracy while protecting license plate information

Experimental results show reduced private information leakage

Abstract

Traffic scene analysis is important for emerging technologies such as smart traffic management and autonomous vehicles. However, such analysis also poses potential privacy threats. For example, a system that can recognize license plates may construct patterns of behavior of the corresponding vehicles' owners and use that for various illegal purposes. In this paper we present a system that enables traffic scene analysis while at the same time preserving license plate privacy. The system is based on a multi-task model whose latent space is selectively compressed depending on the amount of information the specific features carry about analysis tasks and private information. Effectiveness of the proposed method is illustrated by experiments on the Cityscapes dataset, for which we also provide license plate annotations.