Abstract Hemispherical photography produces the most accurate results when working with well-exposed photographs acquired under diffuse light conditions (diffuse-light images). Obtaining such data can be prohibitively expensive when surveying hundreds of plots is required. A relatively inexpensive alternative is using photographs acquired under direct sunlight (sunlight images). However, this practice leads to high errors since the standard processing algorithms expect diffuse-light imagery. Here, instead of using classification algorithms, which is the unique dominant practice, we approached the processing of sunlight images using deep learning (DL) regression. We implemented DL systems by using the general-purpose convolutional neural networks known as VGGNet 16, VGGNet 19, Res-Net, and SE-ResNet. We trained them with 608 samples acquired in a South American temperate forest populated by Nothofagus pumilio. For their evaluation, we used 113 independent samples. Each sample (X, Y) consisted of one or several sunlight images (X), and the plant area index (PAI) and effective PAI (PAIe) extracted from a diffuse-light image (Y). The sunlight images include clear sky and broken clouds with sun elevation from 15° to 47°. We obtained the best results with the SE-ResNet architecture. The system requires a low-resolution input reprojected to cylindrical, and it can make predictions with 10% root mean square error, even from pictures acquired with automatic exposure, which challenge previous findings. Furthermore, similar results (R2= 0.9, n = 104) can be obtained by feeding the system with photographs acquired with an inexpensive fisheye converter attached to a smartphone. Altogether, results indicate that our approach is a cost-efficient option for surveying hundreds of plots under direct sunlight. Therefore, combining our method with the traditional procedures provides processing solutions for virtually all kinds of illumination conditions.

中文翻译：

---

使树冠半球摄影独立于光照条件：一种基于深度学习的方法

摘要 当处理在漫射光条件下获得的曝光良好的照片（漫射光图像）时，半球摄影会产生最准确的结果。当需要调查数百个地块时，获取此类数据可能会非常昂贵。一种相对便宜的替代方法是使用在阳光直射下获取的照片（阳光图像）。然而，这种做法会导致高错误率，因为标准处理算法需要漫射光图像。在这里，我们没有使用作为独特的主导实践的分类算法，而是使用深度学习 (DL) 回归来处理阳光图像。我们通过使用称为 VGGNet 16、VGGNet 19、Res-Net 和 SE-ResNet 的通用卷积神经网络来实现深度学习系统。我们使用在 Nothofagus pumilio 居住的南美温带森林中采集的 608 个样本对它们进行了训练。对于他们的评估，我们使用了 113 个独立样本。每个样本 (X, Y) 由一个或多个阳光图像 (X) 以及从漫射光图像 (Y) 中提取的植物面积指数 (PAI) 和有效 PAI (PAIe) 组成。阳光图像包括晴朗的天空和碎云，太阳高度为 15° 到 47°。我们使用 SE-ResNet 架构获得了最好的结果。该系统需要将低分辨率输入重新投影到圆柱体，它可以以 10% 的均方根误差进行预测，即使是从自动曝光获取的图片中进行预测，这对以前的发现提出了挑战。此外，类似的结果 (R2= 0.9, n = 104) 可以通过向系统提供使用连接到智能手机的廉价鱼眼转换器获取的照片来获得。总而言之，结果表明，我们的方法是在阳光直射下测量数百个地块的经济高效的选择。因此，将我们的方法与传统程序相结合，为几乎所有类型的照明条件提供了处理解决方案。