Data

The challenge involves dataset in the form of road images including damaged parts, collected from the following six countries: India, Japan, Czech Republic, Norway, Unites States, and China (Data for Norway, Unites States, and China, is contributed by the winning data contributors in CRDDC’2022). The damage information is provided as the coordinates of the bounding box and a label depicting the type of damage associated with the box. The following four types of damage are considered: Longitudinal Cracks (D00), Transverse Cracks (D10), Alligator Cracks (D20), and Potholes (D40).

Figure 1: Dataset Statistics (*Test labels are private)

Figure 2: Sample images in the RDD dataset.

The dataset is divided into two parts: Training and Test. The Training set is provided with annotations; however, the test set is purely to test the models and is released without annotations. Check the following links for further details about downloading or analyzing the dataset.

Citations

  1. Arya, D., Maeda, H., Sekimoto, Y., Omata, H., Ghosh, S. K., Toshniwal, D., ... & Kashiyama, T. (2022). RDD2022-The multi-national Road Damage Dataset released through CRDDC’2022. figshare, https://doi.org/10.6084/m9.figshare.21431547.v1
  2. Arya, D., Maeda, H., Ghosh, S. K., Toshniwal, D., & Sekimoto, Y. (2024). RDD2022: A multi-national image dataset for automatic Road Damage Detection. Geoscience Data Journal. https://doi.org/10.1002/gdj3.260
  3. Arya, D., Maeda, H., & Sekimoto, Y. (2024). From Global Challenges to Local Solutions: A Review of Cross-country Collaborations and Winning Strategies in Road Damage Detection. Advanced Engineering Informatics, 60, 102388. https://doi.org/10.1016/j.aei.2024.102388
  4. Arya, D., Maeda, H., Ghosh, S. K., Toshniwal, D., Omata, H., Kashiyama, T., & Sekimoto, Y. (2022a). Crowdsensing-based Road Damage Detection Challenge (CRDDC’2022). In 2022 IEEE International Conference on Big Data (Big Data) (pp. 6378-6386). IEEE.