We present a multidisciplinary forest ecosystem 3D perception dataset. The dataset was collected in the Hainich-Dün region in central Germany, which includes two dedicated areas, which are part of the Biodiversity Exploratories – a long-term research platform for comparative and experimental biodiversity and ecosystem research. The dataset combines several disciplines, including computer science and robotics, biology, bio-geochemistry, and forestry science. We present results for common 3D perception tasks, including classification, depth estimation, localization, and path planning. We combine the full suite of modern perception sensors, including high-resolution fisheye cameras, 3D dense LiDAR, differential GPS, and an inertial measurement unit, with ecological metadata of the area, including stand age, diameter, exact 3D position, and species. The dataset consists of three hand-held measurement series taken from sensors mounted on a UAV during each of three seasons: winter, spring, and early summer. This enables new research opportunities for the forest ecosystem and paves the way for testing forest environment 3D perception tasks and mission set automation.

Three recordings were done during summer, spring and winter in 2 different forest locations HEW5 and HEW45, referred to as forest_1 and forest_2 respectively. The naming of the rosbags refers to the following convention, e.g. abc.bag, where a is either h1 (winter), h2 (spring), h3 (summer), b refers to f1 for HEW5 and f2 for HEW45 and c is an id either r1 or r2. The metadata (manually acquired data by foresters) for all 1967 trees in the experiment area is provided in xlsx file with the following fields: EP − area, Lat, Lon, GKR, GKH , Xm,Ym, Zm, ID, date, DBHmm, Species, multi − stem, brakewood, year, coordinate − system.

The data is stored as follows:

forest_data/

├── winter/

│       ├── forest_1/

│       ├── forest_2/

├── spring/

│       ├── forest_1/

│       ├── forest_2/

├── summer/

│       ├──forest_1/

│       ├──forest_2/

calibration_and_tools/

meta_data/

(accompanied binary raw data of the sensor are simultaneously stored at the following link at Zenodo: https://zenodo.org/record/6891131)

The recorded datasets are zipped into a single file named forest.zip, all data are provided as rosbags (e.g. h1f1r1.bag).

Please combine both zips (Dryad & Zenodo) to include meta-data and raw data.