Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gmayday1997/SceneChangeDet
pytorch implementation of scene change detection
https://github.com/gmayday1997/SceneChangeDet
change-detection contrastive-loss pytorch scene-change-detection
Last synced: about 2 months ago
JSON representation
pytorch implementation of scene change detection
- Host: GitHub
- URL: https://github.com/gmayday1997/SceneChangeDet
- Owner: gmayday1997
- License: mit
- Created: 2018-01-25T10:15:30.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-03-05T03:59:59.000Z (over 1 year ago)
- Last Synced: 2024-02-17T14:36:17.066Z (7 months ago)
- Topics: change-detection, contrastive-loss, pytorch, scene-change-detection
- Language: Python
- Homepage:
- Size: 14 MB
- Stars: 223
- Watchers: 9
- Forks: 74
- Open Issues: 19
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Fully Convolutional Siamese Network for Scene Change Detection
## Requirements
- Python2.7
- Pytorch0.2.0_3 (see: [pytorch installation instuctions](http://pytorch.org/))
- torchvision
## Datasets
This repo is built for scene change detection. We report the performance on three datasets.
- PCD2015 dataset
- paper: [Change detection from a street image pair using cnn features and superpixel segmentation](http://www.vision.is.tohoku.ac.jp/files/9814/3947/4830/71-Sakurada-BMVC15.pdf)
- dataset: http://www.vision.is.tohoku.ac.jp/us/research/4d_city_modeling/pano_cd_dataset/
- VL_CMU_CD dataset
- paper: [Street-view change detection with deconvolutional networks](http://www.robesafe.com/personal/roberto.arroyo/docs/Alcantarilla16rss.pdf)
- dataset: https://ghsi.github.io/proj/RSS2016.html
- CD2014 dataset
- paper: [changedetection.net: A new change detection benchmark dataset](https://www.merl.com/publications/docs/TR2012-044.pdf)
- dataset: http://changedetection.net/
# 06/12/2018 update
We have uploaded the modified CD2014 dataset to [[baiduyun]](https://pan.baidu.com/s/19ReVH6pmizcU79sk2Rsz5w)[[googledrive]](https://drive.google.com/drive/folders/1bUcUZcx8eRFZMsDuzVSo8ZkpLNhkEwNu?usp=sharing),
if you find cd2014 dataset is useful for your research, please cite the paper:
@inproceedings{Goyette2012changedetection,
title={changedetection.net: A New Change Detection Benchmark Dataset},
author={Goyette, Nil and Jodoin, Pierre Marc and Porikli, Fatih and Konrad, Janusz and Ishwar, Prakash},
booktitle={Computer Vision and Pattern Recognition Workshops},
pages={1-8},
year={2012},
}
### Directory Structure
File Structure is as follows:
```
$T0_image_path/*.jpg
$T1_image_path/*.jpg
$ground_truth_path/*.jpg
```
## Pretrained Model
Backbone model, which is deeplabv2 [[baiduyun]](https://pan.baidu.com/s/1Ie8h1Lyzqn2g3GHcGxnppg) [[googledriver]](https://drive.google.com/file/d/1vma3tTX_ecKvInd91CWMEivbxhT5Xjfa/view?usp=sharing)in our work, is available, you should download it and put it to `/pretrain`
Pretrained models for PCD2015 and VL_CMU_CD also have been available.
- PCD2015: [[baiduyun]](https://pan.baidu.com/s/1kNNpRlQZJA45wOf0fJtaxw)
[[googledrive]](https://drive.google.com/file/d/18evxU0Y4CMMe_xBtQu3kj3RAI91ZatE1/view?usp=sharing)
- VL_CMU_CD: [[baiduyun]](https://pan.baidu.com/s/1ZOo3pbJ1hQvx3dSMWXTs-w)
[[googledrive]](https://drive.google.com/file/d/1z2lwbbxhAEvm8w0S55qebp7Q2DokkNG7/view?usp=sharing)
## Training
```shell
cd $SCD_ROOT
python train.py
```