Pheno4D

Notes on the Dataset

  • Only every second scan has instance labels. For the maize plants, also semantic labels are available.

Detailed Information

General Information
NamePheno4D
Release Year2021
Terms of UseUnclear
Access RequirementsNone
Dataset Size4.1 GB
DocumentationIn-depth documentation of acquisition and characteristics of the dataset, e.g., via an explicit dataset paper or a comprehensive multi-page metadata document
CodeYes
ApplicationsVegetation mapping and monitoring | Multi-temporal registration
Detailed ApplicationsPlant growth monitoring (phenotypic trait tracking) | spatio-temporal registration
Acquisition
Number of Scenes14
Number of Epochs per Scene (minimum)11
Number of Epochs per Scene (median)16
Number of Epochs per Scene (maximum)20
General Scene TypeGreenhouse
Specific Scene TypePlant in soil
LocationUnclear
Acquisition TypeStructured light scan
Acquisition DevicePerceptron ScanWorks V5
Acquisition PlatformROMER Infinite 2.0 measuring arm
Scan IntervalHours
Acquisition Months
Representation
Data RepresentationUnstructured, globally aligned (e.g., point cloud or ray cloud)
Specific Data RepresentationPoint cloud
File Format/EncodingTextfile, usually delimiter separated values
Raw Data-
Additional Data-
Coordinate Systemmm
Quality and Usability
RegistrationBetween finely and coarsely registered. The reviewers disagreed on this
Number of Partial Epochs-
Unusable Data Reason-
SplitsNo
Per-Point Attributes
Intensity/ReflectivityNo
ColorNo
Semantic Labels3 | Only some point clouds/parts have labels
Instance LabelsYes | Only some point clouds/parts have labels
Change Labels-
Statistics
Number of Points per Epoch (minimum)337K
Number of Points per Epoch (median)2M
Number of Points per Epoch (maximum)5M
Avg. Point Spacing (minimum)45µm
Avg. Point Spacing (median)67µm
Avg. Point Spacing (maximum)93µm
Avg. Change Points per Epoch-

Paper Reference 1

@article{schunck2021pheno4d,
    title = {Pheno4D: A spatio-temporal dataset of maize and tomato plant point clouds for phenotyping and advanced plant analysis},
    author = {Schunck, David and Magistri, Federico and Rosu, Radu Alexandru and Cornelißen, André and Chebrolu, Nived and Paulus, Stefan and Léon, Jens and Behnke, Sven and Stachniss, Cyrill and Kuhlmann, Heiner and others},
    journal = {Plos one},
    volume = {16},
    number = {8},
    pages = {e0256340},
    year = {2021},
    publisher = {Public Library of Science San Francisco, CA USA},
    doi = {10.1371/journal.pone.0256340},
}