Improving classification of road surface conditions via road area extraction and contrastive learning

TL;DR

This paper presents a low-cost, efficient method for classifying road surface conditions by segmenting road areas and applying contrastive learning, achieving improved accuracy over previous approaches.

Contribution

The study introduces a segmentation-based focus on road surfaces combined with contrastive learning to enhance classification performance with reduced computational costs.

Findings

Significant accuracy improvement over previous methods

Effective segmentation reduces computational load

Contrastive learning enhances classification robustness

Abstract

Maintaining roads is crucial to economic growth and citizen well-being because roads are a vital means of transportation. In various countries, the inspection of road surfaces is still done manually, however, to automate it, research interest is now focused on detecting the road surface defects via the visual data. While, previous research has been focused on deep learning methods which tend to process the entire image and leads to heavy computational cost. In this study, we focus our attention on improving the classification performance while keeping the computational cost of our solution low. Instead of processing the whole image, we introduce a segmentation model to only focus the downstream classification model to the road surface in the image. Furthermore, we employ contrastive learning during model training to improve the road surface condition classification. Our experiments on the public RTK dataset demonstrate a significant improvement in our proposed method when compared to previous works.