Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Paulo Lucas Lucas Figueiredo has a total of 6 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

    1 shared publication
  • Hugo Raposo

    RCM2+—Research Center for Management Engineering and Asset Systems, Institute of Engineering, Polytechnic University of Coimbra, Rua Pedro Nunes—Quinta da Nora, 3030-199 Coimbra, Portugal

    1 shared publication
  • Ivon Brandão

    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
  • José Torres Farinha

    RCM2+—Research Center for Management Engineering and Asset Systems, Institute of Engineering, Polytechnic University of Coimbra, Rua Pedro Nunes—Quinta da Nora, 3030-199 Coimbra, Portugal

    1 shared publication
  • Mateus Mendes

    Coimbra Institute of Engineering, Polytechnic University of Coimbra, Rua Pedro Nunes, 3030-199 Coimbra, Portugal

    1 shared publication
  • 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

    1 shared publication

Latest Publications

  • Open Access

    Benchmarking YOLOv11m-Seg, U-Net++ and Mask R-CNN Networks as a Tool for Assessing Forest Plantation Success

    by Paulo Lucas Figueiredo, Ivon Brandão, Beatriz Fidalgo, Raúl Salas-González, Mateus Mendes

    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

    Forecasting the Life Cycle Assessment in a Cellulose Factory

    by Paulo Lucas Lucas Figueiredo, Hugo David Nogueira Raposo, José Torres Farinha

    The purpose of this article is to explain the introduction of simple and adaptive expo-nential smoothing methods in Life Cycle Cycle Assessment (LCA) and their results. In this case, on a cellulose factory wood debarking and cutting line. Based on a case study in which various life cycle models were applied to this asset, the application of expo-nential smoothing methods to forecast operating and maintenance costs for the t+1 pe-riod was explained; therefore, the period subsequent to the known values. The aim was to include a well-established mathematical tool in the calculation of this value, as it gives the equipment manager an idea of what is coming in the near future. Given that all forecasts end up having a Root Mean Square Error (RSME) associated with them, taking into account the actual value obtained in the previous period, this tool ends up being self-correcting and is expected to minimize the absolute error over time and as the sample size increases. Five different exponential smoothing models were applied: one simple exponential smoothing and four with adaptive parameters. As expected, it was observed that there were different results between the various methods applied. Bear-ing in mind the sample used, “Exponential smoothing with adaptive alpha 2” was the method that presented the smallest error in its forecasts, when compared to the actual values. Regardless of this specific result, the aim is for these models to be applied throughout the entire life of the asset, as well as to several different assets. So that even more detailed conclusions can be drawn about the behavior of the models in different contexts. Life cycle models are becoming increasingly reliable. With the application of robust tools to fill previously unresolved gaps, any manager and/or engineer in any field, who knows and can interpret the data collected from the asset for which they are responsible, will be able to obtain excellent results in its management. Optimizing its useful life and maximizing its availability.