Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Sobre

Sobre

Germano Moreira (GM) received a B.S. and an M.Sc. in Agricultural Engineering at Sciences Faculty - University of Porto (FCUP) and is now attending the 1st year of the PhD in Agricultural Sciences, at the same institution. Recently became a Research Assistant at the Institute for Systems and Computer Engineering, Technology and science (INESC TEC), TEC4AGRO-FOOD, Centre for Robotics in Industry and Intelligent Systems (CRIIS), as a member of the multidisciplinary team of the Laboratory of Robotics and IoT for Smart Precision Agriculture and Forestry, where he will integrate several projects and develop research on Artificial Intelligence (AI) and Computer Vision (CV) to support different agricultural operations. GM's research interests include various topics in Agronomy and Agricultural Engineering mostly focused on Precision Agriculture (PA) and the implementation of Robotics, AI, CV, and Deep Learning in an agricultural context for Crop monitoring and phenotyping. Throughout his academic journey, he participated in two EU-funded INESC TEC projects: AGRINUPES (Water JPI) - Integrated monitoring and control of water, nutrients and plant protection products towards a sustainable agricultural sector - and ROBOCARE (FEDER) - Robotic Platforms for IntelligentPrecision Crops - the latter being the framework for his master's thesis entitled "Tomato Robotic Harvesting in Protected Horticulture: Machine Learning Techniques for Fruit Detection and Classification" which was awarded a final grade of 20/20. GM was the (co)author of 4 scientific publications (ResearchGate) with a total of 14 citations - 3 articles and 1 book chapter - published in journals listed in JCR-WoS and/or SCOPUS, with the most recent publication as the first author being selected for the cover story of Issue 2, Volume 12, of MDPI'sjournal Agronomy (https://www.mdpi.com/2073-4395/12/2/356). Among other outputs, it is worth mentioning aconference poster presented at the 13th Young Research Meeting of the University of Porto (IJUP). GM is amember of IAAS (International Association of Students of Agriculture and Related Sciences), holding the roleof president of the local assembly of the Porto committee from 2019 to 2021. During that period, he enteredthe "24H Agriculture by Syngenta" competition and was part of the team responsible for organising the "IIJourney of Agronomic Engineering FCUP" event. He also participated in events such as "The Digital (R)evolution in Agro-Food and Forestry", "Mechanization and Automation in Slope Viticulture" and attendedthe "International Summer School Agricultural Robotics", organised by PhenoRob (https://www.phenorob.de/),which allowed him to enhance his knowledge in the Agriculture 4.0 field.

Tópicos
de interesse
Detalhes

Detalhes

  • Nome

    Germano Filipe Moreira
  • Cargo

    Assistente de Investigação
  • Desde

    09 fevereiro 2022
006
Publicações

2023

Toward Grapevine Digital Ampelometry Through Vision Deep Learning Models

Autores
Magalhaes, SC; Castro, L; Rodrigues, L; Padilha, TC; de Carvalho, F; dos Santos, FN; Pinho, T; Moreira, G; Cunha, J; Cunha, M; Silva, P; Moreira, AP;

Publicação
IEEE SENSORS JOURNAL

Abstract
Several thousand grapevine varieties exist, with even more naming identifiers. Adequate specialized labor is not available for proper classification or identification of grapevines, making the value of commercial vines uncertain. Traditional methods, such as genetic analysis or ampelometry, are time-consuming, expensive, and often require expert skills that are even rarer. New vision-based systems benefit from advanced and innovative technology and can be used by nonexperts in ampelometry. To this end, deep learning (DL) and machine learning (ML) approaches have been successfully applied for classification purposes. This work extends the state of the art by applying digital ampelometry techniques to larger grapevine varieties. We benchmarked MobileNet v2, ResNet-34, and VGG-11-BN DL classifiers to assess their ability for digital ampelography. In our experiment, all the models could identify the vines' varieties through the leaf with a weighted F1 score higher than 92%.

2023

Deep Learning YOLO-Based Solution for Grape Bunch Detection and Assessment of Biophysical Lesions

Autores
Pinheiro, I; Moreira, G; da Silva, DQ; Magalhaes, S; Valente, A; Oliveira, PM; Cunha, M; Santos, F;

Publicação
AGRONOMY-BASEL

Abstract
The world wine sector is a multi-billion dollar industry with a wide range of economic activities. Therefore, it becomes crucial to monitor the grapevine because it allows a more accurate estimation of the yield and ensures a high-quality end product. The most common way of monitoring the grapevine is through the leaves (preventive way) since the leaves first manifest biophysical lesions. However, this does not exclude the possibility of biophysical lesions manifesting in the grape berries. Thus, this work presents three pre-trained YOLO models (YOLOv5x6, YOLOv7-E6E, and YOLOR-CSP-X) to detect and classify grape bunches as healthy or damaged by the number of berries with biophysical lesions. Two datasets were created and made publicly available with original images and manual annotations to identify the complexity between detection (bunches) and classification (healthy or damaged) tasks. The datasets use the same 10,010 images with different classes. The Grapevine Bunch Detection Dataset uses the Bunch class, and The Grapevine Bunch Condition Detection Dataset uses the OptimalBunch and DamagedBunch classes. Regarding the three models trained for grape bunches detection, they obtained promising results, highlighting YOLOv7 with 77% of mAP and 94% of the F1-score. In the case of the task of detection and identification of the state of grape bunches, the three models obtained similar results, with YOLOv5 achieving the best ones with an mAP of 72% and an F1-score of 92%.

2023

Automated Infield Grapevine Inflorescence Segmentation Based on Deep Learning Models

Autores
Moreira, G; Magalhães, SA; dos Santos, FN; Cunha, M;

Publicação
IECAG 2023

Abstract

2022

Benchmark of Deep Learning and a Proposed HSV Colour Space Models for the Detection and Classification of Greenhouse Tomato

Autores
Moreira, G; Magalhaes, SA; Pinho, T; dos Santos, FN; Cunha, M;

Publicação
AGRONOMY-BASEL

Abstract
The harvesting operation is a recurring task in the production of any crop, thus making it an excellent candidate for automation. In protected horticulture, one of the crops with high added value is tomatoes. However, its robotic harvesting is still far from maturity. That said, the development of an accurate fruit detection system is a crucial step towards achieving fully automated robotic harvesting. Deep Learning (DL) and detection frameworks like Single Shot MultiBox Detector (SSD) or You Only Look Once (YOLO) are more robust and accurate alternatives with better response to highly complex scenarios. The use of DL can be easily used to detect tomatoes, but when their classification is intended, the task becomes harsh, demanding a huge amount of data. Therefore, this paper proposes the use of DL models (SSD MobileNet v2 and YOLOv4) to efficiently detect the tomatoes and compare those systems with a proposed histogram-based HSV colour space model to classify each tomato and determine its ripening stage, through two image datasets acquired. Regarding detection, both models obtained promising results, with the YOLOv4 model standing out with an F1-Score of 85.81%. For classification task the YOLOv4 was again the best model with an Macro F1-Score of 74.16%. The HSV colour space model outperformed the SSD MobileNet v2 model, obtaining results similar to the YOLOv4 model, with a Balanced Accuracy of 68.10%.

2022

Assessing the potential use of drainage from open soilless production systems: A case study from an agronomic and ecotoxicological perspective

Autores
Santos, MG; Moreira, GS; Pereira, R; Carvalho, SMP;

Publicação
AGRICULTURAL WATER MANAGEMENT

Abstract
Cascade cropping systems in soilless horticulture (where drainage collected from the main crop is used in fertigation of secondary crops) are potentially interesting for Mediterranean countries as they enhance water and nutrient use efficiency. However, their agronomic and long-term environmental impact has been poorly addressed. In this case study, lettuce grown hydroponically or in soil (previously exposed to drainage for five years) was fertigated, throughout the cultivation period, with a nutrient solution composed of 0, 25, 50 or 100 % of drainage (0D, 25D, 50D and 100D) mixed with a fresh nutrient solution. Plant performance analysis included growth parameters and leaf mineral composition. Drainage was analyzed for nutrients and Plant Protection Products (PPP) residues, and bioassays were performed exposing aquatic organisms (Raphidocelis subcapitata, Aliivibrio fischeri and Daphnia magna) to drainage and soil elutriate. When analyzing plant performance in both cultivation systems, a significant effect was only found at 100D in hydroponics, resulting in 41 % less leaf area, 20 % smaller head diameter and 43 % lower yield. Drainage analysis showed high nutrient content, presence of PPP residues (up to 6 substances, reaching 3.29 mu g.L-1 in total) and revealed toxicity to D. magna (EC50 = 66.6 %). Moreover, soil elutriate presented toxicity to R. subcapitata (EC50 = 20.6 %) and to A. fischeri (EC50 = 14.9 %). This study demonstrates the potential of using relatively high drainage percentages (up to 50 %) from soilless cultivation systems if applied to hydroponically-grown secondary crops. However, attention should be paid to the use of cascade cropping systems when drainages are applied to fertigate soil-grown crops, as it may contribute to soil degradation and environmental pollution on a long run.