Underwood et al.

Notes on the Dataset

  • Each epoch is scanned from different positions that can be fused into one point cloud.
  • In contrast to the other scenes, for the "sim" scene the y-axis faces upwards, which get corrected when applying the given pose.

Detailed Information

General Information
NameUnderwood et al.
Release Year2013
Terms of UseUnclear
Access RequirementsNone
Dataset Size365.7 MB
DocumentationBetween medium-length (multi-paragraph) and short (multi-line) description. The reviewers disagreed on this
CodeYes
ApplicationsBuilt environment change detection and classification
Detailed Applications3D change detection considering different sensor positions (and therefore occlusions)
Acquisition
Number of Scenes3
Number of Epochs per Scene (minimum)2
Number of Epochs per Scene (median)2
Number of Epochs per Scene (maximum)4
General Scene TypeBuilt
Specific Scene TypeCarpark | lab
LocationUnclear
Acquisition TypeTerrestrial laser scanning
Acquisition DeviceSimulation and Velodyne HDL64ES2
Acquisition PlatformUnclear
Scan IntervalMinutes
Acquisition Months
Representation
Data RepresentationUnstructured, local (e.g., local point clouds or laser scans with poses)
Specific Data RepresentationLocal point clouds
File Format/EncodingTextfile, usually delimiter separated values
Raw Data-
Additional Data-
Coordinate Systemm
Quality and Usability
RegistrationFinely registered
Number of Partial Epochs-
Unusable Data Reason-
SplitsNo
Per-Point Attributes
Intensity/ReflectivityNo
ColorNo
Semantic Labels-
Instance LabelsNo
Change Labels3
Statistics
Number of Points per Epoch (minimum)194K
Number of Points per Epoch (median)1M
Number of Points per Epoch (maximum)1M
Avg. Point Spacing (minimum)6.0mm
Avg. Point Spacing (median)7.9mm
Avg. Point Spacing (maximum)2.2dm
Avg. Change Points per Epoch1.01%

Paper Reference 1

@inproceedings{underwood2013changedetectiondataset,
    author = {James Patrick Underwood and
                  D. Gillsjo and
                  Tim Bailey and
                  Vsevolod Vlaskine},
    title = {Explicit 3D change detection using ray-tracing in spherical coordinates},
    booktitle = {IEEE International Conference on Robotics and Automation, Karlsruhe,
                  Germany, May 6-10, 2013},
    pages = {4735--4741},
    year = {2013},
    doi = {10.1109/ICRA.2013.6631251},
}