ruirangerfan / unsupervised_disparity_map_segmentation

Road Damage Detection Based on Unsupervised Disparity Map Segmentation (T-ITS)

Home Page:https://www.ruirangerfan.com/pdf/tits2019_fan.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unsupervised Disparity Map Segmentation for Road Damage Detection

1. Publication

This repository contains the demo code of our paper "Road Damage Detection Based on Unsupervised Disparity Map Segmentation", published in IEEE Transactions on Intelligent Transportation Systems (T-ITS).

2. demo code

Please run tits_source_code.m to visualize the result.

3. Citation

Please cite our papers when using our source code:

@Article{fan2019road_damage,
  author        = {Fan, Rui and Liu, Ming},
  title         = {Road Damage Detection Based on Unsupervised Disparity Map Segmentation},
  journal       = {IEEE Transactions on Intelligent Transportation Systems},
  year          = {2019},
  pages         = {1--6},
  issn          = {1524-9050},
  doi           = {10.1109/TITS.2019.2947206},
  keywords      = {Road damage detection, disparity map segmentation, stereo rig roll angle, road disparity projection model, numerical solution.},
  url           = {https://ieeexplore.ieee.org/document/8890001},
}
@article{fan2020pothole,
  title={Pothole Detection Based on Disparity Transformation and Road Surface Modeling},
  author={Fan, Rui and Ozgunalp, Umar and Hosking, Brett and Liu, Ming and Pitas, Ioannis},
  journal={IEEE Transactions on Image Processing},
  volume={29},
  pages={897--908},
  year={2020}
}
@inproceedings{fan2019real,
  title={Real-time dense stereo embedded in a uav for road inspection},
  author={Fan, Rui and Jiao, Jianhao and Pan, Jie and Huang, Huaiyang and Shen, Shaojie and Liu, Ming},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year={2019}
}

4. Contact

e-mail: rui.fan@ieee.org

About

Road Damage Detection Based on Unsupervised Disparity Map Segmentation (T-ITS)

https://www.ruirangerfan.com/pdf/tits2019_fan.pdf

License:MIT License


Languages

Language:MATLAB 74.0%Language:TeX 26.0%