RESULTS: A CNN-based one-dimensional deep learning model with spectral attention module was utilized for the estimate of the total chlorophyll of greenhouse lettuce from the full spectrum of hyperspectral images. Experimental results demonstrate that the deep neural network with spectral attention module outperformed the existing standard approaches, including partial least squares regression (PLSR) and random forest (RF), with an average R2 of 0.746 and an average RMSE of 2.018.
CONCLUSIONS: This study unveils the capability of leveraging deep attention networks and hyperspectral imaging for estimating lettuce chlorophyll levels. This approach offers a convenient, non-destructive, and effective estimation method for the automatic monitoring and production management of leafy vegetables.
结果:基于CNN的一维深度学习模型与光谱注意模块用于从高光谱图像的全光谱估计温室莴苣的总叶绿素。实验结果表明,带光谱注意模块的深度神经网络优于现有的标准方法,包括偏最小二乘回归(PLSR)和随机森林(RF),平均R2为0.746,平均RMSE为2.018。
结论:这项研究揭示了利用深度关注网络和高光谱成像来估计莴苣叶绿素水平的能力。这种方法提供了一种方便的,非破坏性的,叶类蔬菜的自动监测和生产管理的有效估算方法。