The Fuji-SfM dataset contains a set of colour images of 11 Fuji apple trees used in  to detect and 3D locate apples by combining instance segmentation neural networks and structure-from-motion (SfM) photogrammetry. The dataset includes: (1) 2D images and the corresponding annotations for training and validate the Mask-RCNN (fruit detection and segmentation), (2) images used to generate the 3D model of 11 Fuji apple trees by using SfM, and (3) the 3D point cloud of the scanned scene with the corresponding apple locations ground truth.
Find more information about this dataset in .
Figure 1. Illustration of Fuji-SfM dataset. a) Colour images with the corresponding instance segmentation annotations. b) Camera postions and point cloud generated using structure-from-motion photogrammetry.
The dataset can be downloaded from the following link: Fuji-SfM dataset (6.43 GB)
This dataset 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 should refer to the following papers:
 Gené-Mola J, Sanz-Cortiella R, Rosell-Polo JR, Morros J-R, Ruiz-Hidalgo J, Vilaplana V, , Gregorio E. 2020. Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry. Computers and Electronics in Agriculture, 169 (2020), 105165. DOI: /10.1016/j.compag.2019.105165
 Gené-Mola J, Sanz-Cortiella R, Rosell-Polo JR, Morros J-R, Ruiz-Hidalgo J, Vilaplana V, , Gregorio E. 2020. Fuji-SfM dataset: a collection of annotated images and point clouds for Fuji apple detection and location using structure-from-motion photogrammetry. Data in Brief (2020), 105591. DOI: /10.1016/j.dib.2020.105591