The officail codebase of VideoPipe dataset. We will update the data and code of our VideoPipe. [Project] [Arxiv]
ToDo
- Update the code of champion team on VideoPipe.
-
[2023-03-08]: We have open the test leaderboards for these two competitions, and you can submit your results on codalab for your research.
-
[2022-03-05]: We have published competitions for VideoPipe ICPR2022 Track: Temporal Defect Localization.
-
[2022-03-05]: We have published competitions for VideoPipe ICPR2022 Track: Video Defect Classification.
- raw videos: You should obey the terms and conditions and download them from our competition pages.
- eval_detection.py：Evaluation code for Track: Temporal Defect Localization.
- eval_classification.py：Evaluation code for Track: Video Defect Classification.
Any question about our VideoPipe, you can email me. ([email protected])
If you think this project is helpful, please feel free to leave a star⭐️ and cite our paper:
@inproceedings{liu2022videopipe,
title={VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection},
author={Liu, Yi and Zhang, Xuan and Li, Ying and Liang, Guixin and Jiang, Yabing and Qiu, Lixia and Tang, Haiping and Xie, Fei and Yao, Wei and Dai, Yi and others},
booktitle={2022 26th International Conference on Pattern Recognition (ICPR)},
pages={4967--4973},
year={2022},
organization={IEEE}
}