Transfer Learning-based Road Damage Detection for Multiple Countries
This work addresses the need for affordable and efficient road damage monitoring solutions for municipalities and road authorities in multiple countries, though it is incremental in building on existing smartphone-based methods.
The paper tackles the problem of automated road damage detection for municipalities lacking resources by assessing a Japanese model's usability for other countries, proposing a large-scale dataset of 26,620 images from multiple countries, and developing generalized models for cross-country detection and classification.
Many municipalities and road authorities seek to implement automated evaluation of road damage. However, they often lack technology, know-how, and funds to afford state-of-the-art equipment for data collection and analysis of road damages. Although some countries, like Japan, have developed less expensive and readily available Smartphone-based methods for automatic road condition monitoring, other countries still struggle to find efficient solutions. This work makes the following contributions in this context. Firstly, it assesses the usability of the Japanese model for other countries. Secondly, it proposes a large-scale heterogeneous road damage dataset comprising 26620 images collected from multiple countries using smartphones. Thirdly, we propose generalized models capable of detecting and classifying road damages in more than one country. Lastly, we provide recommendations for readers, local agencies, and municipalities of other countries when one other country publishes its data and model for automatic road damage detection and classification. Our dataset is available at (https://github.com/sekilab/RoadDamageDetector/).