ChangeDet
Notes on the Dataset
- The (predicted) change points are stored redundantly in a separate file and could be used to annotate the original point cloud.
- The point clouds contains no ground points due to the photogrammetric creation from side-facing cameras.
Detailed Information
| General Information | |
| Name | ChangeDet |
| Release Year | 2021 |
| Terms of Use | Free use for research |
| Access Requirements | None |
| Dataset Size | 6.8 GB | Partial download is possible, i.e. the data is split into several files (e.g., epochs or data types) |
| Documentation | Multi-paragraph description of the dataset, e.g., in the form of a paper section or a comprehensive readme file |
| Code | Yes |
| Applications | Built environment change detection and classification |
| Detailed Applications | Sparse point cloud change detection |
| Acquisition | |
| Number of Scenes | 2 |
| 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 district |
| Location | Singapore |
| Acquisition Type | Photogrammetric from gound-level images |
| Acquisition Device | Wide-angle color cameras + COLMAP |
| Acquisition Platform | Car |
| Scan Interval | Months |
| Acquisition Months | |
| Representation | |
| Data Representation | Unstructured, globally aligned (e.g., point cloud or ray cloud) |
| Specific Data Representation | Point cloud |
| File Format/Encoding | PCD |
| Raw Data | - |
| Additional Data | COLMAP results | RGB images with change annotations |
| Coordinate System | 32648 |
| Quality and Usability | |
| Registration | Finely registered |
| Number of Partial Epochs | - |
| Unusable Data Reason | - |
| Splits | No |
| Per-Point Attributes | |
| Intensity/Reflectivity | No |
| Color | Yes |
| Semantic Labels | - |
| Instance Labels | No |
| Change Labels | 2 | The labels can be computed from other data/mapped to the point cloud, i.e., it can not trivially be done during point cloud construction (at least not for all epochs) |
| Statistics | |
| Number of Points per Epoch (minimum) | 1M |
| Number of Points per Epoch (median) | 1M |
| Number of Points per Epoch (maximum) | 2M |
| Avg. Point Spacing (minimum) | 1.8dm |
| Avg. Point Spacing (median) | 1.9dm |
| Avg. Point Spacing (maximum) | 2.1dm |
| Avg. Change Points per Epoch | 4.44% |
Paper Reference 1
@inproceedings{yew2021datasetchangedet,
author = {Zi Jian Yew and
Gim Hee Lee},
title = {City-scale Scene Change Detection using Point Clouds},
booktitle = {IEEE International Conference on Robotics and Automation, ICRA},
pages = {13362--13369},
year = {2021},
doi = {10.1109/ICRA48506.2021.9561855},
}