Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learning

TL;DR

This paper introduces a new dataset for weather, light level, and street type classification in autonomous driving, along with a baseline model and active learning approach to optimize data selection for robust perception in challenging conditions.

Contribution

It presents the first dataset focused on weather and light classification for autonomous driving, with an active learning framework to efficiently select training data.

Findings

ResNet18 achieves state-of-the-art on public datasets but lower accuracy on this new dataset.

The dataset contains 60k images with 9 labels including weather, light, and street type.

Active learning reduces dataset size from 60k to 1.1k images for effective training.

Abstract

Autonomous driving is rapidly advancing, and Level 2 functions are becoming a standard feature. One of the foremost outstanding hurdles is to obtain robust visual perception in harsh weather and low light conditions where accuracy degradation is severe. It is critical to have a weather classification model to decrease visual perception confidence during these scenarios. Thus, we have built a new dataset for weather (fog, rain, and snow) classification and light level (bright, moderate, and low) classification. Furthermore, we provide street type (asphalt, grass, and cobblestone) classification, leading to 9 labels. Each image has three labels corresponding to weather, light level, and street type. We recorded the data utilizing an industrial front camera of RCCC (red/clear) format with a resolution of $1024\times1084$. We collected 15k video sequences and sampled 60k images. We implement an active learning framework to reduce the dataset's redundancy and find the optimal set of frames for training a model. We distilled the 60k images further to 1.1k images, which will be shared publicly after privacy anonymization. There is no public dataset for weather and light level classification focused on autonomous driving to the best of our knowledge. The baseline ResNet18 network used for weather classification achieves state-of-the-art results in two non-automotive weather classification public datasets but significantly lower accuracy on our proposed dataset, demonstrating it is not saturated and needs further research.