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 Fc, which are used together with artificial neural networks (ANN) to model the relationship between VIs, Fc 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 Fc (geometric approach) to predict vineyard yield results in higher accuracy (root mean square error (RMSE) = 0.9 kg vine−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.

中文翻译：

---

结合遥感、计算机视觉和人工神经网络技术估算葡萄园产量

在葡萄栽培中，预测不同葡萄园区域的生产力水平以进行适当的种植实践至关重要。为了克服这一挑战，通过结合植被指数 (VI) 来感知作物的健康状况并通过计算机视觉获得植被覆盖率 (Fc) 作为衡量植物活力的指标，从而预测最终产量。从无人机 (UAV) 获得的多光谱图像用于获得 VI 和 Fc，它们与人工神经网络 (ANN) 一起用于模拟 VI、Fc 和产量之间的关系。建议的方法应用于葡萄园，在那里应用了不同的灌溉和施肥剂量。结果表明，在精密葡萄栽培中，使用计算机视觉技术区分冠层和土壤是获得准确结果的必要条件。此外，结合 VIs（反射率方法）和 Fc（几何方法）来预测葡萄园产量导致更高的准确度（均方根误差 (RMSE) = 0.9 kg vine−1 和相对误差 (RE) = 21.8%）接近收获时的图像）与简单使用 VI（RMSE = 1.2 kg vine−1 和 RE = 28.7%）相比。机器学习技术的实施导致比线性模型更准确的结果（RMSE = 0.5 kg vine-1 和 RE = 12.1%）。在接近收获日期拍摄图像时，可以获得更精确的产量预测，尽管在早期阶段获得了有希望的结果。