/UFCD

A Pytorch-based toolbox for three different change detection tasks, including binary change detection (BCD), semantic change detection (SCD), and building damage assessment (BDA).

Primary LanguagePython

logo

1. Overview of UFCD

UFCD is a Pytorch-based toolbox for three different change detection tasks, including binary change detection (BCD), semantic change detection (SCD), and building damage assessment (BDA).

2. Usage

✈️ Step 1

To get started, clone this repository:

git clone https://github.com/guanyuezhen/UFCD.git

Next, create the conda environment named ufcd by executing the following command:

conda create -n ufcd python=3.8

Install necessary packages:

pip install -r requirements.txt

✈️ Step 2

Prepare the change detection datasets following ./data/README.md.

✈️ Step 3

Train/Test:

sh ./scripts/train.sh  
sh ./scripts/test.sh

3. Currently Supported Models and Datasets

Supported change detection models:

Model Task Paper Link
TFI-GR BCD Remote Sensing Change Detection via Temporal Feature Interaction and Guided Refinement link
A2Net BCD/SCD Lightweight Remote Sensing Change Detection With Progressive Feature Aggregation and Supervised Attention link
AR-CDNet BCD/BDA Towards Accurate and Reliable Change Detection of Remote Sensing Images via Knowledge Review and Online Uncertainty Estimation link
A2Net SCD Lightweight Remote Sensing Change Detection With Progressive Feature Aggregation and Supervised Attention link
SCanNet/TED SCD Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images link
BiSRNet/SSCDL SCD Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images link
ChangeOS BDA Building Damage Assessment for Rapid Disaster Response with a Deep Object-based Semantic Change Detection Framework: From Natural Disasters to Man-made Disasters link
ChangeOS-GRM BDA - -

Supported binary change detection datasets:

Model Task Link
LEVIR/LEVIR+ BCD link
SYSU BCD link
S2Looking BCD link
SECOND SCD link
Landsat-SCD SCD link
xView2 BDA link

4. Acknowledgment

This repository is built with the help of the projects:

BIT_CD

PytorchDeepLearing

SCanNet

Simple-Remote-Sensing-Change-Detection-Framework

5. Ending

If you feel our work is useful, please remember to Star and consider citing our work. Thanks!~😘.

@article{Li_2023_A2Net,
        author={Li, Zhenglai and Tang, Chang and Liu, Xinwang and Zhang, Wei and Dou, Jie and Wang, Lizhe and Zomaya, Albert Y.},
        journal={IEEE Transactions on Geoscience and Remote Sensing}, 
        title={Lightweight Remote Sensing Change Detection With Progressive Feature Aggregation and Supervised Attention}, 
        year={2023},
        volume={61},
        number={},
        pages={1-12},
        doi={10.1109/TGRS.2023.3241436}
}
@article{li2022cd,
        author={Li, Zhenglai and Tang, Chang and Wang, Lizhe and Zomaya, Albert Y.},
        journal={IEEE Transactions on Geoscience and Remote Sensing}, 
        title={Remote Sensing Change Detection via Temporal Feature Interaction and Guided Refinement}, 
        year={2022},
        volume={60},
        number={},
        pages={1-11},
        doi={10.1109/TGRS.2022.3199502}
}