Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/granularai/fabric
Urban change model designed to identify changes across 2 timestamps
https://github.com/granularai/fabric
change-detection cnn deep-learning pytorch satellite-imagery sentinel-2 unet unet-3d
Last synced: about 1 month ago
JSON representation
Urban change model designed to identify changes across 2 timestamps
- Host: GitHub
- URL: https://github.com/granularai/fabric
- Owner: granularai
- Created: 2018-11-02T10:03:43.000Z (over 5 years ago)
- Default Branch: igarss2019
- Last Pushed: 2023-09-07T13:38:23.000Z (10 months ago)
- Last Synced: 2024-05-21T08:09:42.992Z (about 2 months ago)
- Topics: change-detection, cnn, deep-learning, pytorch, satellite-imagery, sentinel-2, unet, unet-3d
- Language: Jupyter Notebook
- Homepage:
- Size: 195 MB
- Stars: 61
- Watchers: 7
- Forks: 15
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Lists
- awesome-remote-sensing-change-detection - Papadomanolaki M, Verma S, Vakalopoulou M, et al. Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data
README
# Code for the paper "Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data" (Accepted in IGARSS 2019)
This is the github repository containing the code for the paper ["Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data"](https://sagarverma.github.io/others/CD_IGARSS_2019.pdf) by Maria Papadomanolaki, Sagar Verma, Maria Vakalopoulou, Siddharth Gupta, Konstantinos Karantzalos.
MultiDate-LSTM code is available [here](https://github.com/mpapadomanolaki/UNetLSTM.git).
## Requirements
The code has been tested on:
- 4xNvidia P100 GPU
- Ubuntu 18.04 LTS on 96 vCPUs and 240 GB of RAM (Large scale inference will be slower on other configurations)
- [Pytorch](https://pytorch.org/) v0.4.0
- Opencv 3.0
## Urbanization detection output
## Multidate Sentinel-2 dataset
1. [OSCD](https://rcdaudt.github.io/oscd/)
2. [OSCD + Our Dates](https://engine.granular.ai/organizations/granular/projects/61916375b40d35cba31b0b29/overview)
3. [Pretrained weight for Bi-Date Siamese Model](https://engine.granular.ai/organizations/granular/projects/61916375b40d35cba31b0b29/overview)
## Contact
For any queries, please contact
```
Sagar Verma: [email protected]
```