Here we provide a dataset of 1,243 pothole images which have been annotated as per the YOLO labeling format.
We provide the image and the corresponding labeling in the dataset. We have collected the images of potholes from the web consisting of diverse regions. Here is the directory structure for the dataset:
Pothole Dataset
├── README.md
├── img-1.jpg
├── img-1.txt
├── img-2.jpg
├── img-2.txt
├── ...
├── img-1243.jpg
└── img-1243.txt
You can download the dataset from the following link: https://github.com/jaygala24/pothole-detection/releases/download/v1.0.0/Pothole.Dataset.IVCNZ.zip
We recommend you to refer the following github repository for scripts on depth estimation.
If you consider using our work then please cite using:
@INPROCEEDINGS{9290547,
author={Chitale, Pranjal A. and Kekre, Kaustubh Y. and Shenai, Hrishikesh R. and Karani, Ruhina and Gala, Jay P.},
booktitle={2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)},
title={Pothole Detection and Dimension Estimation System using Deep Learning (YOLO) and Image Processing},
year={2020},
volume={},
number={},
pages={1-6},
doi={10.1109/IVCNZ51579.2020.9290547}}