@misc{cheng_treescope_2023,
  title = { TreeScope: {An} {Agricultural} {Robotics} {Dataset} for {LiDAR}-{Based} {Mapping} of {Trees} in {Forests} and {Orchards} },
  shorttitle = {TreeScope},
  url = {http://arxiv.org/abs/2310.02162},
  arxivdoi = {10.48550/arXiv.2310.02162},
  urldate = {2023-10-06},
  publisher = {arXiv},
  author = {Cheng, Derek and Ojeda, Fernando Cladera and Prabhu, Ankit and Liu, Xu and Zhu, Alan and Green, Patrick Corey and Ehsani, Reza and Chaudhari, Pratik and Kumar, Vijay},
  month = oct,
  year = {2023},
  note = {arXiv:2310.02162 [cs]},
  keywords = {Computer Science - Robotics},
  annote = {Comment: Submitted to 2024 IEEE International Conference on Robotics and Automation (ICRA 2024) for review},
  freepdf = {https://arxiv.org/pdf/2310.02162.pdf},
  website = {https://treescope.org/},
  code = {https://github.com/KumarRobotics/treescope},
  tldr = {Dataset paper. Acquired LiDAR scans of forestry and large orchard trees (almond, pistachio) from under the canopy, using small UAVs or a mobile unit in a backpack or cart. Provides semantic segmentation labels of scans for tree stems, ground, and misc. Provides ground truth diameter at breast height (DBH) measurements. Baseline semantic segmentation methods are RangeNet++, SqueezeSegV2, and SqueezeSegV3. Baseline diameter estimation methods are DBCRE and SLOAM.}
}

Data collection for forestry, timber, and agriculture currently relies on manual techniques which are labor-intensive and time-consuming. We seek to demonstrate that robotics offers improvements over these techniques and accelerate agricultural research, beginning with semantic segmentation and diameter estimation of trees in forests and orchards. We present TreeScope v1.0, the first robotics dataset for precision agriculture and forestry addressing the counting and mapping of trees in forestry and orchards. TreeScope provides LiDAR data from agricultural environments collected with robotics platforms, such as UAV and mobile robot platforms carried by vehicles and human operators. In the first release of this dataset, we provide ground-truth data with over 1,800 manually annotated semantic labels for tree stems and field-measured tree diameters. We share benchmark scripts for these tasks that researchers may use to evaluate the accuracy of their algorithms. Finally, we run our open-source diameter estimation and off-the-shelf semantic segmentation algorithms and share our baseline results.

arXiv: http://doi.org/10.48550/arXiv.2310.02162
pdf: https://arxiv.org/pdf/2310.02162.pdf
code: https://github.com/KumarRobotics/treescope
web: https://treescope.org/