Resultados de investigación

Multitask Deep Neural Network for Fruit Detection and Regresion of Fruit Diameters in RGB-D images (based on Detectron2). This project is an extension of the MaskRCNN architecture that allows to compute the diameter of fruits along with performing instance segmentation. The baseline for this project has been the detectron2 implementation of the MaskRCNN (https://github.com/facebookresearch/detectron2).

Apple size estimation using photogrammetry-derived 3D point clouds. This project is a matlab implementation for apple size estimation in 3D point clouds. Four different size estimation methods are implemented: largest segment, least squares, MSAC and template matching.

AKFruitData. This repository contents source code of two applications presented in the article https://doi.org/10.1016/j.softx.2022.101231 at the time of its publication in SoftwareX Journal. The emergence of low-cost 3D sensors, and particularly RGB-D cameras, together with recent advances in artificial intelligence, is currently driving the development of in-field methods for fruit detection, size measurement and yield estimation. However, as the performance of these methods depends on the availability of quality fruit datasets, the development of ad-hoc software to use RGB-D cameras in agricultural environments is essential. The AKFruitData software introduced in this work aims to facilitate use of the Azure Kinect RGB-D camera for testing in field trials. This software presents a dual structure that addresses both the data acquisition and the data creation stages. The acquisition software (AK_ACQS) allows different sensors to be activated simultaneously in addition to the Azure Kinect. Then, the extraction software (AK_FRAEX) allows videos generated with the Azure Kinect camera to be processed to create the datasets, making available colour, depth, IR and point cloud metadata. AKFruitData has been used by the authors to acquire and extract data from apple fruit trees for subsequent fruit yield estimation. Moreover, this software can also be applied to many other areas in the framework of precision agriculture, thus making it a very useful tool for all researchers working in fruit growing.

AKFruitData - ak_acquisition_system is a software solution for data acquisition in fruit orchards using a sensor system boarded on a terrestrial vehicle. It allows the coordination of computers and sensors through the sending of remote commands via a GUI. https://doi.org/10.1016/j.softx.2022.101231. AK_ACQS is a software solution for data acquisition in fruit orchards using a sensor system boarded on a terrestrial vehicle. It allows the coordination of computers and sensors through the sending of remote commands via a GUI. At the same time, it adds an abstraction layer on library stack of each sensor, facilitating its integration. This software solution is supported by a local area network (LAN), which connects computers and sensors from different manufacturers ( cameras of different technologies, GNSS receiver) for in-field fruit yield testing.

This project is a pytorch implementation of a Faster R-CNN for fruit detection suitable with multi-modal images (up to 5 channels). It's based on implementation of: jwyang/faster_rcnn.pytorch, developed based on Pytorch + Numpy This implementation has been used to train and test the KFuji RGB-DS dataset, which contains images with 3 different modalities: colour (RGB), depth(D), and range-corrected intensity signal (S).

Fuji apple dataset for on-tree apple detection and measurment containing 3925 images annotated with modal and amodal segmentation masks and fruit diameter ground truth. This dataset was used to train the deep learning architecture published at https://github.com/GRAP-UdL-AT/Amodal_Fruit_Sizing. The resulting trained model is available by downloading in the file: model_000999.pth

This file contains the replication data for the paper "The Economics of Lost Knowledge: Modeling the Knowledge Cost Due to Non-FAIR Data Practices." It includes the two networks used in the paper, arXiv and OpenAlex, a SQLite database to check whether a link is available on the internet, and the raw network as extracted from arXiv. Aquest fitxer conté les dades de replicació de l’article "L’economia del coneixement perdut: modelant el cost del coneixement degut a pràctiques de dades no FAIR." Inclou les dues xarxes utilitzades a l’article, arXiv i OpenAlex, una base de dades SQLite per comprovar si un enllaç està disponible a internet, i la xarxa en brut tal com va ser extreta d’arXiv. Este archivo contiene los datos de replicación del artículo "La economía del conocimiento perdido: modelando el coste del conocimiento debido a prácticas de datos no FAIR." Incluye las dos redes utilizadas en el artículo, arXiv y OpenAlex, una base de datos SQLite para comprobar si un enlace está disponible en internet, y la red en bruto tal como fue extraída de arXiv.

This file contains Python scripts used for the paper "The Economics of Lost Knowledge: Modeling the Knowledge Cost Due to Non-FAIR Data Practices." making easy to replicate and reuse the data from the paper.

Self-efficacy plays a fundamental role in preparing students for clinical practice. The Physiotherapist Self-Efficacy (PSE) questionnaire was developed to evaluate this aspect in physical therapy students. This dataset was created to validate the translation and cultural adaptation of the questionnaire into Spanish from Spain (PSE-sp). A two-phase study was conducted following international guidelines for the translation process and the evaluation of the psychometric properties of the PSE-sp. Undergraduate physiotherapy students from the University of Lleida and the University of Malaga took part in the study. After completing the translation, the psychometric properties—including structural validity, internal consistency, test–retest reliability, measurement error, convergent validity, and known-groups validity—were assessed. The PSE-sp assesses self-efficacy beliefs related to learning content within the field of physiotherapy through 13 items. Original version in English (Australia) was validated. The self-efficacy belief was evaluated with a Likert scales (1 = very low confidence; 5 = very high confidence). The instrument takes approximately 10 minutes to complete. The General Self-Efficacy Scale (Spanish version) was used as a reference measure.

Pupil dynamics data for the article Pupil dynamics reveal the tuning of tortricid moths to diel activity. It contains pseudopupil brightness curves under no stimulation and under bright UV stimulation on three tortricid species: Grapholita molesta, Lobesia botrana and Cydia pomonella. It also has all Matlab and R code to perform statistics, calculations and figure plotting.