Laboratory for Image & Video Engineering

DeepWaterMap: Surface Water Mapping by Deep Learning

F. Isikdogan, A.C. Bovik, and P. Passalacqua

---

New Version!!!

This project is moved to GitHub. Find the latest version at https://github.com/isikdogan/deepwatermap.

Related Papers

If you find our code, models, or dataset useful in your research, please cite our papers:
• L. F. Isikdogan, A.C. Bovik, and P. Passalacqua, "Seeing Through the Clouds with DeepWaterMap," IEEE Geoscience and Remote Sensing Letters, 2019.
• F. Isikdogan, A.C. Bovik, and P. Passalacqua, "Surface Water Mapping by Deep Learning," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017.

Pretrained Models

Running the models require the Caffe deep learning framework.

Model definitions

• MLP benchmark model
• DeepWaterMap-1
• DeepWaterMap-3
• DeepWaterMap-5

Trained weights

• MLP benchmark model
• DeepWaterMap-1
• DeepWaterMap-3
• DeepWaterMap-5

Demo

A package that includes an example scene, a script to run the models, and example results:

• Demo

Training

The models were trained using a modified version of Caffe.

• MLP benchmark model
• DeepWaterMap-1
• DeepWaterMap-3
• DeepWaterMap-5
• Solver

---