Ivon Brandão
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ivon Brandão has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Beatriz Fidalgo
Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua da Misericórdia, Lagar dos Cortiços, São Martinho do Bispo, 3045-093 Coimbra, Portugal
3 shared publications - Raúl Salas-González
Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua da Misericórdia, Lagar dos Cortiços, São Martinho do Bispo, 3045-093 Coimbra, Portugal
3 shared publications - Mateus Mendes
Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua Pedro Nunes, 3030-199 Coimbra, Portugal
2 shared publications - Paulo Lucas Lucas Figueiredo
Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua da Misericórdia, Lagar dos Cortiços, São Martinho do Bispo, 3045-093 Coimbra, Portugal
1 shared publication - Pedro Apóstolo
RCM2+—Research Center in Asset Management and Systems Engineering, Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua Pedro Nunes, 3030-199 Coimbra, Portugal
1 shared publication
Latest Publications
- Open Access
- 12 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11205
Benchmarking YOLOv11m-Seg, U-Net++ and Mask R-CNN Networks as a Tool for Assessing Forest Plantation Success
Monitoring forest plantations is a challenging task that normally requires tree counting on the ground. The task can be challenging and time-consuming, especially in areas of difficult access. The monitoring process proposed in the present research is based on several images collected via flights of a DJI Mavic 3M drone. A number of these images were collected, selected and processed to optimise the training, validation and testing of the developed algorithms. Three models were compared, including YOLOv11m-seg, U-Net++ and Mask R-CNN networks, to understand the pros and cons of using each one of these algorithms for object detection, counting and segmenting tree crowns with RGB images obtained via UAV. In order to develop a tool to assist in the evaluation of planting success, images were collected in Serra do Açor, Arganil, Coimbra, Portugal. The results were promising, as YOLOv11m-seg and Mask R-CNN achieved instance F1 scores of 86.8% and 87.8%, respectively, with the latter demonstrating greater accuracy in plantation areas. At the pixel level, IoU was 78.1% for U-Net++, 77.3% for Mask R-CNN and 76.7% for YOLOv11m-seg. YOLOv11m-seg was the fastest model on the CPU, running at 1.0 s per tile, compared to 3.3 s for Mask R-CNN and 5.8 s for U-Net++. It also predicted the fewest false tree crowns outside the plantation’s areas. This demonstrates the viability of the methodology and that model selection will rely on monitoring needs (as summarised in a decision matrix in this document). This method reduces costs and labour time, increasing the possibility of comparing aerial images more frequently, which will support decision-making in forest management.
- 12 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11205
Open AccessBenchmarking YOLOv11m-Seg, U-Net++ and Mask R-CNN Networks as a Tool for Assessing Forest Plantation Success
Monitoring forest plantations is a challenging task that normally requires tree counting on the ground. The task can be challenging and time-consuming, especially in areas of difficult access. The monitoring process proposed in the present research is based on several images collected via flights of a DJI Mavic 3M drone. A number of these images were collected, selected and processed to optimise the training, validation and testing of the developed algorithms. Three models were compared, including YOLOv11m-seg, U-Net++ and Mask R-CNN networks, to understand the pros and cons of using each one of these algorithms for object detection, counting and segmenting tree crowns with RGB images obtained via UAV. In order to develop a tool to assist in the evaluation of planting success, images were collected in Serra do Açor, Arganil, Coimbra, Portugal. The results were promising, as YOLOv11m-seg and Mask R-CNN achieved instance F1 scores of 86.8% and 87.8%, respectively, with the latter demonstrating greater accuracy in plantation areas. At the pixel level, IoU was 78.1% for U-Net++, 77.3% for Mask R-CNN and 76.7% for YOLOv11m-seg. YOLOv11m-seg was the fastest model on the CPU, running at 1.0 s per tile, compared to 3.3 s for Mask R-CNN and 5.8 s for U-Net++. It also predicted the fewest false tree crowns outside the plantation’s areas. This demonstrates the viability of the methodology and that model selection will rely on monitoring needs (as summarised in a decision matrix in this document). This method reduces costs and labour time, increasing the possibility of comparing aerial images more frequently, which will support decision-making in forest management.
- Open Access
- 18 September 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (9) , 801
An Open-Source Handheld Mobile LiDAR Pipeline for Tree Detection, Stem Reconstruction and Volume Estimation in Pinus pinaster Stands
Forests play a critical role in biodiversity and in the conservation of ecosystems. Reliable and efficient forest inventories are therefore essential for sustainable forest management. Handheld mobile laser scanning (HMLS) is operationally attractive for forest inventory but has rarely been validated against a destructive reference in Mediterranean Pinus pinaster stands. We propose an open-source five-phase HMLS pipeline comprising PDAL pre-processing with CSF ground classification, TLS2trees segmentation, CSF-anchored per-tree setup, slice-wise stem reconstruction with a sequential RANSAC prior, a one-parameter species-specific shape model, and analytical volume integration with a form-factor sanity clamp. The pipeline is calibrated against a destructive reference of 45 Pinus pinaster trees across four plots in central Portugal. Leave-one-plot-out cross-validation produces a volume MAPE of 9.9%, a height MAPE of 4.4% and a DBH MAPE of 3.9%. On the matched sub-sample for which the FJD Trion S1 manufacturer software and a manual CloudCompare workflow also have outputs, the proposed pipeline is competitive with the manual workflow on volume and delivers the lowest median DBH error of the three methods, while remaining fully open-source and reporting per-tree quality and uncertainty diagnostics alongside every estimate.
- 18 September 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (9) , 801
Open AccessAn Open-Source Handheld Mobile LiDAR Pipeline for Tree Detection, Stem Reconstruction and Volume Estimation in Pinus pinaster Stands
Forests play a critical role in biodiversity and in the conservation of ecosystems. Reliable and efficient forest inventories are therefore essential for sustainable forest management. Handheld mobile laser scanning (HMLS) is operationally attractive for forest inventory but has rarely been validated against a destructive reference in Mediterranean Pinus pinaster stands. We propose an open-source five-phase HMLS pipeline comprising PDAL pre-processing with CSF ground classification, TLS2trees segmentation, CSF-anchored per-tree setup, slice-wise stem reconstruction with a sequential RANSAC prior, a one-parameter species-specific shape model, and analytical volume integration with a form-factor sanity clamp. The pipeline is calibrated against a destructive reference of 45 Pinus pinaster trees across four plots in central Portugal. Leave-one-plot-out cross-validation produces a volume MAPE of 9.9%, a height MAPE of 4.4% and a DBH MAPE of 3.9%. On the matched sub-sample for which the FJD Trion S1 manufacturer software and a manual CloudCompare workflow also have outputs, the proposed pipeline is competitive with the manual workflow on volume and delivers the lowest median DBH error of the three methods, while remaining fully open-source and reporting per-tree quality and uncertainty diagnostics alongside every estimate.
- Open Access
Storm Damage and Planting Success Assessment in Pinus pinaster Aiton Stands Using Mask R-CNN
In Portugal, increasing wildfire frequency and severe storm events have intensified the need for advanced monitoring tools to assess forest damage and recovery efficiently. This study explores the application of deep learning neural network techniques, specifically the Mask R-CNN architecture, for the automatic detection of trees in Pinus pinaster stands using RGB and multispectral imagery captured by a drone. The research addresses two distinct forest scenarios, resulting from disturbances intensified by climate change. The first concerns the detection of fallen trees following an extreme weather event to support damage assessment and inform post-disturbance forest management. The second focuses on segmenting individual trees in a newly established plantation after wildfire to evaluate the effectiveness of ecological restoration efforts. The collected images were processed to generate high-resolution orthophotos and orthomosaics, which were used as input for tree detection using Mask R-CNN. Results showed that integrating drone-based imagery with deep learning models can significantly enhance the efficiency of forest assessments, reducing the need for fieldwork effort and increasing the reliability of the collected data. Results demonstrated high performance, with average precision scores of 90% for fallen trees and 75% for recently planted trees, while also enabling the extraction of spatial metrics relevant to forest monitoring. Overall, the proposed methodology shows strong potential for rapid response in post-disturbance environments and for monitoring the early development of forest plantations.
Open AccessStorm Damage and Planting Success Assessment in Pinus pinaster Aiton Stands Using Mask R-CNN
In Portugal, increasing wildfire frequency and severe storm events have intensified the need for advanced monitoring tools to assess forest damage and recovery efficiently. This study explores the application of deep learning neural network techniques, specifically the Mask R-CNN architecture, for the automatic detection of trees in Pinus pinaster stands using RGB and multispectral imagery captured by a drone. The research addresses two distinct forest scenarios, resulting from disturbances intensified by climate change. The first concerns the detection of fallen trees following an extreme weather event to support damage assessment and inform post-disturbance forest management. The second focuses on segmenting individual trees in a newly established plantation after wildfire to evaluate the effectiveness of ecological restoration efforts. The collected images were processed to generate high-resolution orthophotos and orthomosaics, which were used as input for tree detection using Mask R-CNN. Results showed that integrating drone-based imagery with deep learning models can significantly enhance the efficiency of forest assessments, reducing the need for fieldwork effort and increasing the reliability of the collected data. Results demonstrated high performance, with average precision scores of 90% for fallen trees and 75% for recently planted trees, while also enabling the extraction of spatial metrics relevant to forest monitoring. Overall, the proposed methodology shows strong potential for rapid response in post-disturbance environments and for monitoring the early development of forest plantations.