Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Mário Cunha

2023

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

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

Publication
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%.

2021

MODELING SPATIAL-TEMPORAL WINE YIELD BASED on LAND SURFACE TEMPERATURE, VEGETATION INDICES and GIS - The CASE of the DOURO WINE REGION

Authors
Moreira P.; Duarte L.; Cunha M.; Teodoro A.C.;

Publication
International Geoscience and Remote Sensing Symposium (IGARSS)

Abstract
This work aims to integrate Remote Sensing (RS) and cadastral data in QGIS software to perform the spatiotemporal mapping of Wine Yield (WY) cluster zones in the Douro region. Spatiotemporal modelling approach for prediction of wine yield was based on Normalized Difference Vegetation Index (NDVI), Land Surface Temperature (LST) and topographic data. The results showed that 74% (R2 = 0.744, n=128, p<0.000) WY interannual variability at administrative division could be explained by the developed model. This information allows establishing wine production region pattern which can improve the agronomic and economic efficiency of vineyard and winery operations.

2003

Airborne pollen concentration in the region of Braga, Portugal, and its relationship with meteorological parameters

Authors
Ribeiro, H; Cunha, M; Abreu, I;

Publication
Aerobiologia

Abstract
The variation in airborne pollen concentration of the Braga region (Portugal) was studied in springtime, during the flowering of Vitis vinifera. The data set was obtained for two consecutive years (1999 and 2000), using a Cour-type sampler. During this period, thirty-six taxa were observed in a total of 3,200 pollen grains m-3 of air (CPA). The main pollen types observed were Olea, Poaceae and Castanea, representing 74% of the pollen spectrum. The airborne pollen concentration (CPA) was significantly correlated with certain meteorological parameters. Pollen concentration was positively correlated with temperature and wind direction (East and Northeast) and negatively correlated with rainfall and number of rainy days.

2008

The importance of plantain (Plantagospp.) as a supplementary pollen source in the diet of honey bees

Authors
Sabugosa-Madeira, B; Ribeiro, H; Cunha, M; Abreu, I;

Publication
Journal of Apicultural Research

Abstract

2008

The newest generation of Paul Wurth bell-less top® blast furnace charging systems

Authors
Brinckmann, J; Dele, R; Goffin, R; Kinsch, P; Thillen, G; Cunha, M;

Publication
ANNALS - 3rd International Meeting on Ironmaking and 2nd International Symposium on Iron Ore

Abstract
The Paul Wurth Bell-Less Top® (BLT) is the industrial standard for iron blast furnace charging systems. Since Paul Wurth's invention of the BLT in the early 1970s the system has evolved with the changes in iron-making technologies and market conditions. With the latest demands for high charging equipment availability and maintainability - new developments have been recently implemented. The paper will cover the evolution of the Bell-Less Top®, the latest operational requirements and the latest new developments and solutions.

2011

Remote sensing based indicators of changes in a mountain rural landscape of Northeast Portugal

Authors
Pocas, I; Cunha, M; Pereira, LS;

Publication
APPLIED GEOGRAPHY

Abstract
Landscape metrics were used to analyze landscape changes and related driving forces in a mountain rural landscape of Northeast Portugal over three decades. This landscape has great heterogeneity, which favors high levels of diversity and provides for a variety of habitats. The landscape metrics were obtained from land cover maps derived from Landsat images of 1979, 1989 and 2002. Results indicate a trend for increased landscape fragmentation, decrease of annual crop fields (-43%) and, mainly, increase of meadows (+60%). Results relate with decline and aging of the rural population, and to several measures and policies of subsidies implemented in the region in application of the Common Agriculture Policy, which contributed to the replacement of annual crops by meadows. Results are potentially useful to base appropriate policies for landscape management and conservation planning.

  • 9
  • 22