Published Data Sets

Authors: Gené-Mola, J.; Gregorio, E., Auat, F., Guevara, J., Llorens, J., Sanz-Cortiella, R., Escolà, A., Rosell-Polo, J.R., 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, 105248. https://doi.org/10.1016/j.dib.2020.105248

Abstract: This article presents the LFuji-air dataset, which contains LiDAR based point clouds of 11 Fuji apples trees and the corresponding apples location ground truth. A mobile terrestrial laser scanner (MTLS) comprised of a LiDAR sensor and a real-time kinematics global navigation satellite system was used to acquire the data. The MTLS was mounted on an air-assisted sprayer used to generate different air flow conditions. A total of 8 scans per tree were performed, including scans from different LiDAR sensor positions (multi-view approach) and under different air flow conditions. These variability of the scanning conditions allows to use the LFuji-air dataset not only for training and testing new fruit detection algorithms, but also to study the usefulness of the multi-view approach and the application of forced air flow to reduce the number of fruit occlusions. The data provided in this article is related to the research article entitled “Fruit detection, yield prediction and canopy geometric characterization using LiDAR with forced air flow”

Authors: Gené-Mola, J., Sanz-Cortiella, R., Rosell-Polo, J.R., Morros, J.R., Ruiz-Hidalgo, J., Vilaplana, V., Gregorioa, 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 30, 105591. https://doi.org/10.1016/j.dib.2020.105591

Abstract: The present dataset contains colour images acquired in a commercial Fuji apple orchard (Malus domestica Borkh. cv. Fuji) to reconstruct the 3D model of 11 trees by using structure-from-motion (SfM) photogrammetry. The data provided in this article is related to the research article entitled “Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry” [1]. The Fuji-SfM dataset includes: (1) a set of 288 colour images and the corresponding annotations (apples segmentation masks) for training instance segmentation neural networks such as Mask-RCNN; (2) a set of 582 images defining a motion sequence of the scene which was used to generate the 3D model of 11 Fuji apple trees containing 1455 apples by using SfM; (3) the 3D point cloud of the scanned scene with the corresponding apple positions ground truth in global coordinates. With that, this is the first dataset for fruit detection containing images acquired in a motion sequence to build the 3D model of the scanned trees with SfM and including the corresponding 2D and 3D apple location annotations. This data allows the development, training, and test of fruit detection algorithms either based on RGB images, on coloured point clouds or on the combination of both types

Authors: Gené-Mola, J., Llorens, J., Rosell-Polo, J.R., Gregorio, E., Arnó, J., Solanelles, F., Martínez-Casasnovas, J.A., Escolà, A., 2020. KEvOr dataset. Zenodo, https://doi.org/10.5281/zenodo.4286460

Abstract: The Kinect Evaluation in Orchard conditions (KEvOr) dataset is comprised of a set of RGB-D captures carried out with the Microsoft Kinect v2 to evaluate the performance of this sensor at different lighting conditions in agricultural orchards and from different distances to the measured target. Three Microsoft Kinect v2 sensors (K2S1, K2S2 and K2S3) were used to scan Fuji apple trees along the afternoon and evening, from the higher sun illuminance (55000 lux) until achieving dark conditions (0.1 lux), obtaining a total of 252 captures: 28 lighting conditions * 3 sensors * 3 repetitions. The data provided for each capture is: the acquired point cloud, illuminance level at the center of the measured scene, and wind speed. The sensors where placed as follows: K2S1: Oriented to the north, measuring the row of trees side under direct sunlight. This sensor was placed at 2.5 m from the measured target; K2S2: Oriented to the north, measuring the row of trees side under direct sunlight. This sensor was placed at 1.5 m from the measured target; K2S3 Oriented to the south, measuring the row of trees side under indirect sunlight. This sensor was placed at 2.5 m from the measured target; The dataset also includes two additional registered captures measuring the same scene from 1.5 m and from 2.5 m.

Authors: Gené-Mola, J.,Sanz-Cortiella, R., Rosell-Polo, J.R., Escolà, A., Gregorio, E., 2021. PFuji-Size dataset: A collection of images and photogrammetry-derived 3D point clouds with ground truth annotations for Fuji apple detection and size estimation in field conditions. Data in Brief 39, 107629. https://doi.org/10.1016/j.dib.2021.107629

The PFuji-Size dataset is comprised of a collection of 3D point clouds of Fuji apple trees (Malus domestica Borkh. cv. Fuji) scanned at different maturity stages and annotated for fruit detection and size estimation. Structure-from-motion and multi-view stereo techniques were used to generate the 3D point clouds of 6 complete Fuji apple trees containing a total of 615 apples. The resulting point clouds were 3D segmented by identifying the 3D points corresponding to each apple (3D instance segmentation), obtaining a single point cloud for each apple. All segmented apples were labelled with ground truth diameter annotations. Since the data was acquired in field conditions and at different maturity stages, the set includes different fruit diameters -from 26.9 mm to 94.8 mm- and different fruit occlusion percentages due to foliage. In addition, 25 apples were photographed 360° in laboratory conditions, obtaining high resolution 3D point clouds of this sub-set. To the best of the authors’ knowledge, this is the first publicly available dataset for apple size estimation in field conditions. This dataset was used to evaluate different fruit size estimation methods in the research article titled “In-field apple size estimation using photogrammetry-derived 3D point clouds: comparison of 4 different methods considering fruit occlusion”.

Authors: Gené-Mola, J., Ferrer-Ferrer, M., Gregorio, E., Blok, P.M., Hemming, J., Morros, J.R., Rosell-Polo, J.R., Vilaplana, V., Ruiz-Hidalgo, J. 2023. Looking behind occlusions: A study on amodal segmentation for robust on-tree apple fruit size estimation. Computers and Electronics in Agriculture, 209, 107854. https://doi.org/10.1016/j.compag.2023.107854

We provide a deep-learning method to better estimate the size of partially occluded apples. The method is based on ORCNN (https://github.com/waiyulam/ORCNN) and sizecnn (https://git.wur.nl/blok012/sizecnn), which extended Mask R-CNN network to simultaneously perform modal and amodal instance segmentation. The amodal mask is used to estimate the fruit diameter in pixels, while the modal mask is used to measure in the depth map the distance between the detected fruit and the camera and calculate the fruit diameter in mm by applying the pinhole camera model.

https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing