Vineyard yield estimation by combining remote sensing, computer vision and artificial neural network techniques
- PDF / 1,875,509 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 55 Downloads / 188 Views
Vineyard yield estimation by combining remote sensing, computer vision and artificial neural network techniques Rocío Ballesteros1 · Diego S. Intrigliolo2 · José F. Ortega1 · Juan M. Ramírez‑Cuesta2 · Ignacio Buesa2 · Miguel A. Moreno1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In viticulture, it is critical to predict productivity levels of the different vineyard zones to undertake appropriate cropping practices. To overcome this challenge, the final yield was predicted by combining vegetation indices (VIs) to sense the health status of the crop and by computer vision to obtain the vegetated fraction cover ( Fc) as a measure of plant vigour. Multispectral imagery obtained from an unmanned aerial vehicle (UAV) is used to obtain VIs and F c, which are used together with artificial neural networks (ANN) to model the relationship between VIs, F c and yield. The proposed methodology was applied in a vineyard, where different irrigation and fertilisation doses were applied. The results showed that using computer vision techniques to differentiate between canopy and soil is necessary in precision viticulture to obtain accurate results. In addition, the combination of VIs (reflectance approach) and F c (geometric approach) to predict vineyard yield results in higher accuracy (root mean square error (RMSE) = 0.9 kg v ine−1 and relative error (RE) = 21.8% for the image when close to harvest) compared to the simple use of VIs (RMSE = 1.2 kg vine−1 and RE = 28.7%). The implementation of machine learning techniques resulted in much more accurate results than linear models (RMSE = 0.5 kg vine−1 and RE = 12.1%). More precise yield predictions were obtained when images were taken close to the harvest date, although promising results were obtained at earlier stages. Given the perennial nature of grapevines and the multiple environmental and endogenous factors determining yield, seasonal calibration for yield prediction is required. Keywords Unmanned aerial vehicles · Deficit irrigation · RGB ortho-images · NIR · Rededge · k-means algorithm · Vitis vinifera
* Miguel A. Moreno [email protected] 1
Departamento de Producción Vegetal Y Tecnología Agraria, Universidad de Castilla-La Mancha, Ciudad Real, Spain
2
Centro de Edafología Y Biología Aplicada del Segura. Consejo Superior de Investigaciones Científicas (CEBAS-CSIC), Murcia, Spain
13
Vol.:(0123456789)
Precision Agriculture
Introduction Vineyards, when established for wine production, are complex farming systems where (1) aspects related to crop performance and (2) the resulting grapes and wines compositions are worthy of consideration. In general, with a given climate, the composition of the resulting grape depends largely on the vine crop levels and final yields (Jackson and Lombard 1993). This dependence is because, with high crop demands, vineyard capacity may be limited by berry sugar concentrations and dry matter accumulation (Mirás-Avalos et al. 2016). Owing to this limitation, in many wine-growing reg
Data Loading...
