Logo Agrotecnio















Inici > English version > GRAP publications > LFuji-air dataset

LFuji-air dataset

The LFuji-air dataset contains 3D LiDAR data of 11 Fuji apple trees scanned from different sensor positions and applying different forced air flow conditions, allowing the analysis of using forced air flow and different sensor positioning for fruit detection, yield prediction and geometric characterization.

Pont clouds are saved as matrices in .mat format, where each row corresponds to a 3D point with the following information: [x-coordinate, y-coordinate, z-coordinate, calibrated reflectance]. Each point cloud file corresponds to an apple tree scanned with specific conditions. The file name describes the scanning conditions by the following code:

  • H1: Trial scanned from height 1.8m.
  • H2: Trial scanned from height 2.5m.
  • n: Trial without forced air flow.
  • af: Trial with forced air flow
  • E: Point cloud acquired from the east tree row side.
  • W: Point cloud acquired from the west tree row side.

Find more information about the scanning conditions in [1].

All point clouds were manually annotated with 3D rectangular bounding boxes on each apple position, annotating a total of 1,353 apples in all the dataset. Find annotations in .txt format inside “AllTrees_Groundtruth” folder. Each file corresponds to an apple annotation, where the first eight rows gives the 3D coordinates [x,y,z] of the bounding box corners, and the 9th row corresponds to the bounding box centre.


The dataset can be downloaded from the following link: LFuji-air dataset (451 MB)

Find the baseline used for fruit detection in [1] at fruit_detection_in_LiDAR_pointClouds


This database is available only for research and educational purpose and not for any commercial use. If you use the database in any publications or reports, you must refer to the following papers:

[1] Gené-Mola J, Gregorio E, Auat Cheein F, Guevara J, Llorens J, Sanz-Cortiella R, Escolà A, Rosell-Polo JR. 2020. Fruit detection, yield prediction and canopy geometric characterization using LiDAR with forced air flow. Computers and Electronics in Agriculture, 168 (2020), 105121. DOI: 10.1016/j.compag.2019.105121

[2] Gené-Mola J, Gregorio E, Auat F, Guevara J, Llorens J, Sanz-Cortiella R, Escolà A, Rosell-Polo JR. 2020. LFuji-air dataset: Annotated 3D LiDAR point clouds of Fuji apple trees for fruit detection scanned under different forced air flow conditions. Data in brief, 29 (2020), 105248. DOI: 10.1016/j.dib.2020.105248

Last modified: 24/02/2020
Imprimir Enrera Pujar

Home | Accessibility | About the web | Site map | Legal notice | Contact
© 2014 Universitat de Lleida - Pl. de Víctor Siurana 1, 25003 Lleida - Tel. (+34) 973 702 000 - All rights reserved