License Plate Privacy in Collaborative Visual Analysis of Traffic Scenes
This work addresses privacy concerns for vehicle owners in smart traffic and autonomous vehicle systems, representing an incremental improvement in privacy-preserving techniques for visual analysis.
The paper tackles the problem of preserving license plate privacy during traffic scene analysis by introducing a multi-task model that selectively compresses its latent space based on feature relevance to analysis tasks and private information. The method's effectiveness is demonstrated through experiments on the Cityscapes dataset, which includes new license plate annotations.
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.