Francisco Adrião Silva Oliveira

Mr. Francisco Adrião Silva Oliveira

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2024 in Sensors
Verified
Journal Article
Open access
PDF file
Francisco Adrião Silva OliveiraFrancisco Adrião Silva Oliveira
Francisco Adrião Silva Oliveira
Daniel Queirós da SilvaDaniel Queirós da Silva
Daniel Queirós da Silva
Vítor Jesus FilipeVítor Jesus Filipe
Vítor Jesus Filipe
TPTatiana M. Pinho
Tatiana M. Pinho
Mario CunhaMario Cunha
Mario Cunha
Filipe Neves dos SantosFilipe Neves dos Santos
Filipe Neves dos Santos
Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed us to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection in images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70% and 86.5% with inference times of around 89 ms for an input size of 1280 × 1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.

4 September 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Francisco Adrião Silva OliveiraFrancisco Adrião Silva Oliveira
Francisco Adrião Silva Oliveira
Daniel Queirós da SilvaDaniel Queirós da Silva
Daniel Queirós da Silva
Vítor Jesus FilipeVítor Jesus Filipe
Vítor Jesus Filipe
TPTatiana M. Pinho
Tatiana M. Pinho
Mario CunhaMario Cunha
Mario Cunha
Filipe Neves dos SantosFilipe Neves dos Santos
Filipe Neves dos Santos
Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection on images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70 % and 86.5 % with inference times of around 89 ms for an input size of 1280×1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.

16 November 2024
Verified
Book Chapter
Closed access
PDF file
Francisco Adrião Silva OliveiraFrancisco Adrião Silva Oliveira
Francisco Adrião Silva Oliveira
VTVítor Tinoco
Vítor Tinoco
Antonio ValenteAntonio Valente
Antonio Valente
TPTatiana M. Pinho
Tatiana M. Pinho
J. Boaventura-CunhaJ. Boaventura-Cunha
J. Boaventura-Cunha
Filipe Neves dos SantosFilipe Neves dos Santos
Filipe Neves dos Santos

23 September 2026 in Scientific Data
Verified
Journal Article
Open access
PDF file
Francisco Adrião Silva OliveiraFrancisco Adrião Silva Oliveira
Francisco Adrião Silva Oliveira
JCJoão Castro
João Castro
DSDaniel Queirós da Silva
Daniel Queirós da Silva
JBJosé Boaventura
José Boaventura
MCMário Cunha
Mário Cunha
FSFilipe N. Santos
Filipe N. Santos
Agricultural robotics is becoming increasingly relevant for executing arduous tasks where human labour is scarce. Grapevine pruning is a seasonal task that, when performed manually, requires a worker to perform selective cutting of the grapevine canes. For a robot to conduct this type of task autonomously, it needs to navigate the vineyard rows without colliding with the grapevines, as well as retain information regarding each grapevine to perform the operation. This work presents datasets collected in a vineyard, comprising RGB and depth images, LiDAR and GNSS/RTK data, acquired using both a handheld device and a mobile robot. Furthermore, 494 RGB images obtained from the handheld device recordings were annotated with segmentation masks in YOLO format. The datasets support the development and evaluation of computer vision, localisation, mapping and sensor fusion algorithms for autonomous robots. Technical validation demonstrates the consistency and usability of the annotated data for training deep learning models.

19 May 2026 in Applied Food Research
Verified
Journal Article
Open access
Francisco Adrião Silva OliveiraFrancisco Adrião Silva Oliveira
Francisco Adrião Silva Oliveira
VTVítor Tinoco
Vítor Tinoco
Leandro RodriguesLeandro Rodrigues
Leandro Rodrigues
Filipe Neves dos SantosFilipe Neves dos Santos
Filipe Neves dos Santos
Mario CunhaMario Cunha
Mario Cunha
MSMarisa V. Santos
Marisa V. Santos