Check references & licenses!
- Neural network: DeepCrack
- Code implementation: DeepSegmentor (Pretrained weights)
- WebApp implementation: crack-detector (only-cpu)
Web app powered by AI to detect cracks on surfaces.
Clic here to see the demo of crack-detector in action for images and video (<5 min).
To downloand the image and run the contaider in detach mode, run the code below.
docker container run -p 8501:8501 --rm -d pablogod/crack-detector:latest
To shutdown the docker type this:
docker ps -aq # Check which id was assigned for the crack-detector instance
docker stop <weird id of crack-detector> # Type the id
Run this code locally on Linux based distros:
# Clone and install requirements
git clone https://github.com/DZDL/crack-detector
cd crack-detector
pip3 install -r requirementsDocker.txt
# Download the pretrained weights
gdown --id 12-iXK656aGUIWCtN9gb0Ko7qotyn9ZcI -O myapp/DeepSegmentor/checkpoints/deepcrack/latest_net_G.pth
# Run streamlit
streamlit run app.py
# Then a webapp will open, check console output.
Only maintainers of the repository can do this.
heroku login
docker ps
heroku container:login
heroku container:push web -a crack-detector
heroku container:release web -a crack-detector
Database & code, more info check DeepCrack &DeepSegmentor (Pretrained weights).
@article{liu2019deepcrack,
title={DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation},
author={Liu, Yahui and Yao, Jian and Lu, Xiaohu and Xie, Renping and Li, Li},
journal={Neurocomputing},
volume={338},
pages={139--153},
year={2019},
doi={10.1016/j.neucom.2019.01.036}
}
@article{liu2019roadnet,
title={RoadNet: Learning to Comprehensively Analyze Road Networks in Complex Urban Scenes from High-Resolution Remotely Sensed Images},
author={Liu, Yahui and Yao, Jian and Lu, Xiaohu and Xia, Menghan and Wang, Xingbo and Liu, Yuan},
journal={IEEE Transactions on Geoscience and Remote Sensing},
volume={57},
number={4},
pages={2043--2056},
year={2019},
doi={10.1109/TGRS.2018.2870871}
}