Datasets
Open Access
HRSCD - High Resolution Semantic Change Detection Dataset
- Citation Author(s):
-
RodrigoCaye Daudt
ETH ZürichBertrandLe SauxESAAlexandreBoulchValeo.ai - Submitted by:
- Rodrigo Daudt
- Last updated:
- Thu, 12/15/2022 - 11:33
- DOI:
- 10.21227/azv7-ta17
- Links:
- License:
19048 Views- Categories:
- Keywords:
Abstract
About
Dataset described in:
Daudt, R.C., Le Saux, B., Boulch, A. and Gousseau, Y., 2019. Multitask learning for large-scale semantic change detection. Computer Vision and Image Understanding, 187, p.102783.
This dataset contains 291 coregistered image pairs of RGB aerial images from IGS's BD ORTHO database. Pixel-level change and land cover annotations are provided, generated by rasterizing Urban Atlas 2006, Urban Atlas 2012, and Urban Atlas Change 2006-2012 maps.
The dataset is split into five parts:
- 2006 images
- 2012 images
- Change labels
- 2006 land cover maps
- 2012 land cover maps
Labels
Change labels are available for all image pairs in the dataset. Available classes:
- 0: No change
- 1: Change
Land cover maps are available for all images in the dataset. Urban Atlas classes have been grouped at first hierarchical level, as described in the paper cited above. Available classes:
- 0: No information
- 1: Artificial surfaces
- 2: Agricultural areas
- 3: Forests
- 4: Wetlands
- 5: Water
Citation
If you use this dataset for your work, please use the following citation:
@article{daudt2018hrscd,
title = "Multitask Learning for Large-scale Semantic Change Detection",
journal = "Computer Vision and Image Understanding",
volume = "187",
pages = "102783",
year = "2019",
issn = "1077-3142",
doi = "https://doi.org/10.1016/j.cviu.2019.07.003",
url = "http://www.sciencedirect.com/science/article/pii/S1077314219300992",
author = "Daudt, {Rodrigo Caye} and {Le Saux}, Bertrand and Boulch, Alexandre and Gousseau, Yann",
keywords = "Semantic change detection, High resolution Earth observation, Fully convolutional networks, Remote sensing, Multitask learning"
}
Authors
Rodrigo Caye Daudt, rodrigo.cayedaudt@geod.baug.ethz.ch
Bertrand Le Saux, bls@ieee.org
Alexandre Boulch, alexandre.boulch@valeo.com
Yann Gousseau, yann.gousseau@telecom-paris.fr
Copyright
The images in this dataset are released under IGN's "licence ouverte". More information can be found at http://www.ign.fr/institut/activites/lign-lopen-data
The maps used to generate the labels in this dataset come from the Copernicus program, and as such are subject to the terms described here: https://land.copernicus.eu/local/urban-atlas/change-2006-2009?tab=metada...
This dataset is released under Creative-Commons BY-NC-SA licence. For commercial purposes, please contact the authors.
Please contact us if you have any questions.
Dataset Files
Land cover labels 2006 labels_land_cover_2006.zip (219.99 MB)- Land cover labels 2012 labels_land_cover_2012.zip (220.52 MB)
- Change labels labels_change.zip (20.32 MB)
- Images 2012 images_2012.zip (4.63 GB)
- Images 2006 images_2006.zip (3.48 GB)
README README.txt (2.84 kB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.
Documentation
| Attachment | Size |
|---|---|
| README.txt | 3.26 KB |
Comments
The - BD ORTHO® 50 cm, D 14 - CALVADOS, 2005 and - BD ORTHO® 50 cm, D 35 - ILLE-ET-VILLAINE, 2006 datasets do not appear on the linked IGN webpage provided. Additionally the Geoportail provided is difficult to navigate for those of us who don't speak French. Is there an updated webpage I can access these datasets at? Thank you in advance.
As stated in the dataset description, we do not have the redistribution rights for the 2006 images. Please contact us by email for further help in downloading these images.
Have you got the image data for 2006?
The 2006 images appear to be missing
As stated in the dataset description, we do not have the redistribution rights for the 2006 images. Please contact us by email for further help in downloading these images.
.
All change labels files appear to be blank or else are only comprised of 0's (i.e. "no change"). Is there a way to fix this?
Some people have contacted me with this problem, and it seems that OpenCV sometimes fails to load the labels correctly, I don't know why. Below is a python program you can run to test if the images are corrupted. The output should contain mostly ones and a few zeroes.
import skimage.io as io
from glob import glob
files = glob('change/*/*.tif')
for f in files:
I = io.imread(f)
print(I.max())
Using This dataset, is their a sample project available for semantic change detection. Kindly share any github page, that would be helpful for my research work.
Hi Rodrigo,
The datset looks not correct. The 2006 & 2012 Lancover maps are missing. Also Tiff images present in 2006/2012/change folders all looks simillar. Can you provide the correct dataset and GIThub page Simillar to OSCD dataset.
Thanks,
Visa
Totally agree!!
Thank you for upload. However the "images 2012" zip file consists of 291 single images not pair. Is there anything wrong?
Unique labels for all the land cover maps show 0 instead of 0,1,2,3,4,5. Can you please guide me on this
The 2006 images appear to be missing, and I've contacted you by e-mail, please check.
Thank you for your work on the HRSCD dataset. I noticed that the land cover labels for 2006 and 2012 are exactly the same. Could you confirm if this is correct?