Transfer Learning-based Road Damage Detection for Multiple Countries
arXiv:2008.13101
Abstract
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/).
16 pages, 14 figures
References in corpus (5)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
- Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network
- Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses
Cited by in corpus (7)
- Global Road Damage Detection: State-of-the-art Solutions
- Road Damage Detection and Classification with Detectron2 and Faster R-CNN
- Influence of image noise on crack detection performance of deep convolutional neural networks
- CNN Model & Tuning for Global Road Damage Detection
- Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones
- FasterRCNN Monitoring of Road Damages: Competition and Deployment
- AI Driven Road Maintenance Inspection