Pothole-600 Dataset

Our pothole-600 dataset is publicly available at here. 

You can also access the dataset on Kaggle.

This dataset was collected using a ZED stereo camera. The road disparity images were estimated using PT-SRP [1]; the disparity transformation algorithm was first introduced in [2], and an advanced version was presented later on in [3]. 

If you use our dataset for research purposes, please also consider citing the following works:

[1] Fan, R., Ai, X. and Dahnoun, N., 2018. Road surface 3D reconstruction based on dense subpixel disparity map estimation. IEEE Transactions on Image Processing, 27(6), pp.3025-3035.

[2] Fan, R., Ozgunalp, U., Hosking, B., Liu, M. and Pitas, I., 2019. Pothole detection based on disparity transformation and road surface modeling. IEEE Transactions on Image Processing, 29, pp.897-908.

[3] Fan, R. and Liu, M., 2019. Road damage detection based on unsupervised disparity map segmentation. IEEE Transactions on Intelligent Transportation Systems.