Llibres / Capítols de llibre (Ciència i Enginyeria Forestal i Agrícola)
Permanent URI for this collection
Browse
Recent Submissions
- ItemOpen AccessPerformance assessment of low-cost LiDAR-based sensors and RGB-D cameras in fruit orchards(Wageningen Academic Publishers, 2025) Gregorio López, Eduard; Pallejà Cabrè, Tomàs; Felip Pomés, Marc; Sanz Cortiella, Ricardo; Lanza, B.; Tresanchez Ribes, Marcel; Escolà i Agustí, Alexandre; Plata Moreno, José Manuel; Martínez Casasnovas, José Antonio; Gené Mola, JordiKnowing the geometric and structural characteristics of fruit orchards is essential for properly managing agricultural operations. Light detection and ranging (LiDAR) sensors allow for accurate 3D orchard reconstructions, although their high cost limits their adoption by farmers. In this work, the performance of several RGB-D cameras and emerging low-cost solid-state LiDAR sensors has been evaluated under real orchard conditions. Accuracies of 10–12 mm for the LiDAR sensors and 7 mm for the time-of-flight RGB-D camera have been achieved. These results open new opportunities for the development of low-cost orchard monitoring systems.
- ItemOpen AccessBuenas prácticas fitosanitarias para una mejor calidad del agua(Ministerio de Agricultura, Pesca y Alimentación, 2008) Bernat i Juanós, Carlos; Escolà i Agustí, Alexandre; Llop i Casamada, Jordi; Llorens Calveras, Jordi; Queraltó Alcázar, Meritxell
- ItemOpen AccessConclusions: Future Directions in Sensing for Precision Agriculture(Springer Nature Switzerland AG, 2021) Kerry, Ruth; Escolà i Agustí, AlexandreIn this fnal chapter, we provide an overall conclusion to this book on the use of sensors in precision agriculture (PA) based on the conclusions of the individual chapters concerning key themes and future research needs. The authors highlighted aspects related to the need to improve sensor resolutions (spatial, temporal and spectral), increase accuracy and simplify the process of calibration, when required. The ability to obtain gigabytes or even terabytes of data is complicated by the need to store, process and analyse them. Although computing power is increasing continuously, automated data processes are also required to ease the adoption of new sensing systems. In addition, some barriers to the widespread adoption of sensing approaches in PA are identifed. Most important are economics and training. Gathering, processing and analysing data from sensing systems should lead farmers to make more informed management decisions and that is only possibe if the information derived helps them to increase profts in a sustainable way.
- ItemOpen AccessVideo-Based Fruit Detection and Tracking for Apple Counting and Mapping(IEEE, 2023) Gené Mola, Jordi; Felip Pomés, Marc; Net Barnés, Francesc; Morros Rubió, Josep Ramon; Miranda, Juan Carlos; Arnó Satorra, Jaume; Asin Jones, Luis; Lordan Sanahuja, Jaume; Ruiz Hidalgo, Javier; Gregorio López, EduardAutomatic fruit counting systems have garnered interest from farmers and agronomists to monitor fruit production, predict yields in advance, and identify production variability across orchards. However, accurately counting fruits poses challenges, particularly due to occlusions. This study proposes a multi-view sensing approach using continuous motion videos captured by a camera moved along the row of trees, followed by fruit detection in all video frames and application of Multi-Object Tracking (MOT) algorithms to prevent double-counting. Three tracking methods, namely SORT, DeepSORT, and ByteTrack, are compared for fruit counting using the YOLOv5x object detector. The methodology is applied to map fruit production in an experimental apple orchard at two different dates: four weeks and one week before harvest. The results demonstrate that ByteTrack (MOTA=0.682; IDF1=0.837; HOTA=0.689) outperforms SORT and DeepSORT, indicating its superior tracking performance. Computational efficiency analysis reveals similar processing times between SORT and ByteTrack (about 15 ms), while DeepSORT requires significantly more processing time per image (128 ms). Fruit counting evaluation shows reasonably accurate yield predictions on both dates, with reduced errors and improved performance closer to the harvest date (MAPE=7.47 %; R2=0.70). The system proves effective in estimating orchard fruit production using computer vision technology, offering valuable insights for yield forecasting. These findings contribute to optimizing fruit production and supporting precision agriculture practices. The code and the dataset have been made publicly available and a video visualization of results is accessible at http://www.grap.udl.cat/en/publications/video_fruit_counting.
- ItemOpen AccessLa sanidad vegetal en la agricultura y la silvicultura. Retos y perspectivas para la próxima década(REAL ACADEMIA DE INGENIERÍA DE ESPAÑA, 2023) Jiménez Díaz, Rafael M.; Milagros López, María; Albajes Garcia, Ramon