Mapping tree crowns in arid or semi-arid areas, which cover around one-third of the Earth’s land surface, is a key methodology towards sustainable management of trees. Recent advances in deep learning have shown promising results for tree crown segmentation. However, a large amount of manually labeled data is still required. We here propose a novel method to delineate tree crowns from high resolution satellite imagery using deep learning trained with automatically generated labels from 3D radiative transfer modeling, intending to reduce human annotation significantly. The methodological steps consist of 1) simulating images with a 3D radiative transfer model, 2) image style transfer learning based on generative adversarial network (GAN) and 3) tree crown segmentation using U-net segmentation model. The delineation performances of the proposed method have been evaluated on a manually annotated dataset consisting of more than 40,000 tree crowns. Our approach, which relies solely on synthetic images, demonstrates high segmentation accuracy, with an F1 score exceeding 0.77 and an Intersection over Union (IoU) above 0.64. Particularly, it achieves impressive accuracy in extracting crown areas (r2 greater than 0.87) and crown densities (r2 greater than 0.72), comparable to that of a trained dataset with human annotations only. In this study, we demonstrated that the integration of a 3D radiative transfer model and GANs for automatically generating training labels can achieve performances comparable to human labeling, and can significantly reduce the time needed for manual labeling in remote sensing segmentation applications.

中文翻译：

---

使用 3D 辐射传输建模的自动树冠标记在半干旱景观中的树木分割方面实现了人类相当的性能


在干旱或半干旱地区（约占地球陆地表面的三分之一）绘制树冠图是实现树木可持续管理的关键方法。深度学习的最新进展表明，树冠分割取得了有希望的结果。但是，仍然需要大量手动标记的数据。我们在这里提出了一种新方法，使用深度学习从高分辨率卫星图像中描绘树冠，并使用 3D 辐射传输建模自动生成的标签进行训练，旨在显着减少人工注释。方法步骤包括 1） 使用 3D 辐射迁移模型模拟图像，2） 基于生成对抗网络 （GAN） 的图像风格迁移学习，以及 3） 使用 U-net 分割模型进行树冠分割。所提出的方法的描绘性能已在由 40,000 多个树冠组成的手动注释数据集上进行了评估。我们的方法完全依赖于合成图像，表现出很高的分割准确性，F1 分数超过 0.77，交并比 （IoU） 高于 0.64。特别是，它在提取牙冠面积（r2 大于 0.87）和牙冠密度（r2 大于 0.72）方面取得了令人印象深刻的准确性，与仅使用人工注释的训练数据集相当。在这项研究中，我们证明了 3D 辐射传输模型和 GAN 的集成以自动生成训练标签可以实现与人工标记相当的性能，并且可以显着减少遥感分割应用中手动标记所需的时间。