Patterns of Vehicle Lights: Addressing Complexities in Curation and Annotation of Camera-Based Vehicle Light Datasets and Metrics

TL;DR

This paper discusses the complexities of representing and annotating vehicle lights in datasets for autonomous driving, introduces the LISA Vehicle Lights Dataset, and evaluates different light representations for various driving tasks.

Contribution

It introduces the LISA Vehicle Lights Dataset and Light Visibility Model, addressing annotation challenges and providing insights into optimal vehicle light representations for autonomous driving tasks.

Findings

Different representations have specific strengths and weaknesses.

The LISA dataset improves annotation quality for downstream tasks.

Vehicle light representation impacts detection and prediction accuracy.

Abstract

This paper explores the representation of vehicle lights in computer vision and its implications for various tasks in the field of autonomous driving. Different specifications for representing vehicle lights, including bounding boxes, center points, corner points, and segmentation masks, are discussed in terms of their strengths and weaknesses. Three important tasks in autonomous driving that can benefit from vehicle light detection are identified: nighttime vehicle detection, 3D vehicle orientation estimation, and dynamic trajectory cues. Each task may require a different representation of the light. The challenges of collecting and annotating large datasets for training data-driven models are also addressed, leading to introduction of the LISA Vehicle Lights Dataset and associated Light Visibility Model, which provides light annotations specifically designed for downstream applications in vehicle detection, intent and trajectory prediction, and safe path planning. A comparison of existing vehicle light datasets is provided, highlighting the unique features and limitations of each dataset. Overall, this paper provides insights into the representation of vehicle lights and the importance of accurate annotations for training effective detection models in autonomous driving applications. Our dataset and model are made available at https://cvrr.ucsd.edu/vehicle-lights-dataset