# Winter Road Surface Condition Recognition in Snowy Regions Based on Image-to-Image Translation

## TL;DR

This paper introduces a method to improve road surface recognition in snowy regions by standardizing lighting conditions using image translation, enhancing safety during dusk.

## Contribution

A novel image-to-image translation approach for illumination normalization in road condition classification.

## Key findings

- Illumination normalization via CycleGAN achieved 78% accuracy at dusk.
- The proposed method outperformed conventional time-based switching methods.
- Late Fusion with Extreme Learning Machine improved classification accuracy.

## Abstract

What are the main findings?
Illumination conditions are standardized using image-to-image translation, enabling a classification approach that is more robust than time-based switching methods.Illumination normalization via CycleGAN achieved 78% accuracy at dusk, outperforming conventional methods.

Illumination conditions are standardized using image-to-image translation, enabling a classification approach that is more robust than time-based switching methods.

Illumination normalization via CycleGAN achieved 78% accuracy at dusk, outperforming conventional methods.

What are the implications of the main findings?
Enables improved road condition monitoring without relying on unstable time-based model switching.Enhances winter traffic safety by improving the detection of frozen surfaces even under transitional lighting conditions like dusk.

Enables improved road condition monitoring without relying on unstable time-based model switching.

Enhances winter traffic safety by improving the detection of frozen surfaces even under transitional lighting conditions like dusk.

In snowy regions, road surface conditions change due to snowfall or ice formation in winter. This can lead to very dangerous situations when driving a car. Therefore, recognizing road surface conditions is important for both drivers and road managers. Road surface classification using in-vehicle cameras faces challenges due to the diverse environments in which vehicles operate. It is difficult to build a single classification model that can handle all conditions. One major challenge is illumination. During dusk, it changes rapidly and drastically, resulting in poor classification accuracy. Therefore, a robust method is needed to accurately recognize road conditions at all times. In this study, we used an image translation method to standardize illumination conditions. Next, we extracted features from both the translated images and the original images using MobileNet. Finally, we integrated these features using Late Fusion with an Extreme Learning Machine to classify road conditions. The effectiveness of this method was verified using a dataset of in-vehicle camera images. The results showed that the accuracy of this method achieved 78% during dusk and outperformed the comparison methods. It was confirmed that the uniformity of illumination conditions contributed to the improvement in classification accuracy. The proposed method can classify road conditions even during dusk, when sudden changes in illumination occur. This demonstrates the potential to realize a robust road condition recognition method that contributes to improved driver safety and efficient road management.