3DCD
Notes on the Dataset
- The paper states that the dataset contains 472 pairs of images, but only 471 are available for download.
- 88 of the DSMs contain erroneous parts (black stripes).
- The file train/3D/356-4612_6_6.tif is corrupted and can't be read.
Detailed Information
| General Information | |
| Name | 3DCD |
| Release Year | 2022 |
| Terms of Use | Unclear |
| Access Requirements | None |
| Dataset Size | 2.3 GB | Partial download is possible, i.e. the data is split into several files (e.g., epochs or data types) |
| Documentation | In-depth documentation of acquisition and characteristics of the dataset, e.g., via an explicit dataset paper or a comprehensive multi-page metadata document |
| Code | Yes |
| Applications | Built environment change detection and classification |
| Detailed Applications | 3D change maps from optical images |
| Acquisition | |
| Number of Scenes | 383 | One coherent scene is recorded, but it is split into multiple non-overlapping parts |
| Number of Epochs per Scene (minimum) | 2 |
| Number of Epochs per Scene (median) | 2 |
| Number of Epochs per Scene (maximum) | 2 |
| General Scene Type | Urban |
| Specific Scene Type | City tile |
| Location | Valladolid (Spain) |
| Acquisition Type | Airborne laser scanning |
| Acquisition Device | LEICA ALS50 and LEICA ALS80 |
| Acquisition Platform | Aircraft (plane) |
| Scan Interval | Years |
| Acquisition Months | |
| Representation | |
| Data Representation | Structured, globally aligned (e.g., DSM, DTM, or DEM) |
| Specific Data Representation | Digital surface model |
| File Format/Encoding | GeoTIFF |
| Raw Data | - |
| Additional Data | - |
| Coordinate System | 3042 |
| Quality and Usability | |
| Registration | Finely registered |
| Number of Partial Epochs | - |
| Unusable Data Reason | Errorneous |
| Splits | Yes |
| Per-Point Attributes | |
| Intensity/Reflectivity | No |
| Color | Yes |
| Semantic Labels | - |
| Instance Labels | No |
| Change Labels | 2 |
| Statistics | |
| Number of Points per Epoch (minimum) | 40K |
| Number of Points per Epoch (median) | 40K |
| Number of Points per Epoch (maximum) | 40K |
| Avg. Point Spacing (minimum) | 1.0m |
| Avg. Point Spacing (median) | 1.0m |
| Avg. Point Spacing (maximum) | 2.3m |
| Avg. Change Points per Epoch | 4.59% |
Paper Reference 1
@article{coletta2022dataset3dcd,
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},
doi = {10.5194/isprs-archives-XLIII-B3-2022-1349-2022},
}