Fehr et al.
Notes on the Dataset
- The pointclouds in the ROS bags contain some points with their color erroneously being black, i.e., it is clear from the scene that these surface points were not black in the real world. We filtered them out for our computations.
Detailed Information
| General Information | |
| Name | Fehr et al. |
| Release Year | 2017 |
| Terms of Use | Unclear |
| Access Requirements | None |
| Dataset Size | 127.9 GB | Partial download is possible, i.e. the data is split into several files (e.g., epochs or data types) |
| Documentation | Between medium-length (multi-paragraph) and short (multi-line) description. The reviewers disagreed on this |
| Code | No |
| Applications | Long-term localization and mapping | Dynamic object detection, localization, and modelling |
| Detailed Applications | Long-term SLAM | dynamic object discovery |
| Acquisition | |
| Number of Scenes | 3 |
| Number of Epochs per Scene (minimum) | 4 |
| Number of Epochs per Scene (median) | 9 |
| Number of Epochs per Scene (maximum) | 10 |
| General Scene Type | Indoor |
| Specific Scene Type | Single room |
| Location | Unclear |
| Acquisition Type | Depth camera carried by person |
| Acquisition Device | Integrated RGB-D Camera |
| Acquisition Platform | Google Tango tablet (+ tripod in one case) |
| Scan Interval | Minutes to Days | Educated guess by the authors |
| Acquisition Months | |
| Representation | |
| Data Representation | Unstructured, globally aligned (e.g., point cloud or ray cloud) |
| Specific Data Representation | Point cloud |
| File Format/Encoding | ROS bag |
| Raw Data | RGBD |
| Additional Data | Mesh |
| Coordinate System | m |
| 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 | - |
| Statistics | |
| Number of Points per Epoch (minimum) | 14M |
| Number of Points per Epoch (median) | 17M |
| Number of Points per Epoch (maximum) | 27M |
| Avg. Point Spacing (minimum) | 2.2mm |
| Avg. Point Spacing (median) | 3.1mm |
| Avg. Point Spacing (maximum) | 3.7mm |
| Avg. Change Points per Epoch | - |
Paper Reference 1
@inproceedings{fehr2017datasettsdfobjectdiscovery,
author = {Fehr, Marius and Furrer, Fadri and Dryanovski, Ivan and Sturm, Jürgen and Gilitschenski, Igor and Siegwart, Roland and Cadena, Cesar},
booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
title = {TSDF-based change detection for consistent long-term dense reconstruction and dynamic object discovery},
year = {2017},
pages = {5237--5244},
doi = {10.1109/ICRA.2017.7989614},
}