Global Road Damage Detection: State-of-the-art Solutions

TL;DR

This paper reviews the top solutions from the Global Road Damage Detection Challenge, highlighting the use of YOLO-based ensemble methods that achieved around 0.66-0.67 F1 scores for automatic road damage detection across diverse datasets.

Contribution

It presents the top methods and insights from a large-scale international challenge focused on automatic road damage detection using deep learning models.

Findings

YOLO-based ensemble learning achieved high F1 scores (~0.66-0.67).

The challenge involved diverse datasets from India, Japan, and Czech Republic.

Insights on effective strategies and areas for improvement in road damage detection.

Abstract

This paper summarizes the Global Road Damage Detection Challenge (GRDDC), a Big Data Cup organized as a part of the IEEE International Conference on Big Data'2020. The Big Data Cup challenges involve a released dataset and a well-defined problem with clear evaluation metrics. The challenges run on a data competition platform that maintains a leaderboard for the participants. In the presented case, the data constitute 26336 road images collected from India, Japan, and the Czech Republic to propose methods for automatically detecting road damages in these countries. In total, 121 teams from several countries registered for this competition. The submitted solutions were evaluated using two datasets test1 and test2, comprising 2,631 and 2,664 images. This paper encapsulates the top 12 solutions proposed by these teams. The best performing model utilizes YOLO-based ensemble learning to yield an F1 score of 0.67 on test1 and 0.66 on test2. The paper concludes with a review of the facets that worked well for the presented challenge and those that could be improved in future challenges.