3DCD Dataset

3DCD Dataset

Main novelty of 3DCD Dataset:

3DCD Dataset allows the development of deep learning algorithms that can infer 3D CD maps using only remote sensing optical bitemporal images as input without the need of Digital Elevation Models (DEMs)

Composition of the dataset:

  • pairs of optical images acquired in 2010 and in 2017

  • the corresponding 2D CD maps in raster format (.tiff)

  • the corresponding 3D CD maps in raster format (.tiff)

  • pairs of DSMs covering the same area and years (.tiff)

The orthophotos and LiDAR data are from the "Centro de Descarga Nacional" website and cover the urban area of Valladolid (Spain)

News

  • [10/05/2022] 3DCD dataset can be downloaded! See Download section!

  • [27/05/2022] 3DCD was presented at LPS2022 as a poster contribution!

  • [31/05/2022] Our arxiv preprint Inferring 3D change detection from bitemporal optical images is now online at this link!

  • [31/05/2022] Our paper 3DCD: a new dataset for 2D and 3D change detection using deep learning techniques is now online at this link!

  • [07/06/2022] 3DCD will be presented at ISPRS Congress 2022 in Nice as a poster contribution! Hope to see you there!

  • [13/09/2022] A new version of the dataset is now available! See Download section!

  • [10/12/2022] Code has been released at https://github.com/VMarsocci/3DCD!

  • [13/01/2023] Our paper Inferring 3D change detection from bitemporal optical images has been accepted in ISPRS Journal of Photogrammetry and Remote Sensing! Check it at the link!

Citation

If you found our work useful, consider citing these works:

@article{MARSOCCI2023325,

title = {Inferring 3D change detection from bitemporal optical images},

journal = {ISPRS Journal of Photogrammetry and Remote Sensing},

volume = {196},

pages = {325-339},

year = {2023},

issn = {0924-2716},

doi = {https://doi.org/10.1016/j.isprsjprs.2022.12.009},

url = {https://www.sciencedirect.com/science/article/pii/S0924271622003240},

author = {Valerio Marsocci and Virginia Coletta and Roberta Ravanelli and Simone Scardapane and Mattia Crespi},

keywords = {3D change detection, Remote sensing, Deep learning, Elevation change detection, Dataset},

}

@Article{isprs-archives-XLIII-B3-2022-1349-2022,

AUTHOR = {Coletta, V. and Marsocci, V. and Ravanelli, R.},

TITLE = {3DCD: A NEW DATASET FOR 2D AND 3D CHANGE DETECTION USING DEEP LEARNING TECHNIQUES},

JOURNAL = {The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},

VOLUME = {XLIII-B3-2022},

YEAR = {2022},

PAGES = {1349--1354},

URL = {https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B3-2022/1349/2022/},

DOI = {10.5194/isprs-archives-XLIII-B3-2022-1349-2022}

}