A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting
This addresses safety issues for autonomous driving systems in challenging environments, but it is incremental as it builds on existing datasets and methods.
The authors tackled the problem of perception algorithms for autonomous vehicles performing poorly in adverse weather and lighting by creating A-BDD, a synthetic dataset of over 60,000 augmented images, and showed that data augmentations can significantly reduce performance gaps in these conditions.
High-autonomy vehicle functions rely on machine learning (ML) algorithms to understand the environment. Despite displaying remarkable performance in fair weather scenarios, perception algorithms are heavily affected by adverse weather and lighting conditions. To overcome these difficulties, ML engineers mainly rely on comprehensive real-world datasets. However, the difficulties in real-world data collection for critical areas of the operational design domain (ODD) often means synthetic data is required for perception training and safety validation. Thus, we present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K that are equipped with semantic segmentation and bounding box annotations (inherited from the BDD100K dataset). The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We further introduce novel strategies utilizing feature-based image quality metrics like FID and CMMD, which help identify useful augmented and real-world data for ML training and testing. By conducting experiments on A-BDD, we provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.