当前位置: X-MOL 学术IEEE Geosci. Remote Sens. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Filling Voids in Elevation Models Using a Shadow-Constrained Convolutional Neural Network
IEEE Geoscience and Remote Sensing Letters ( IF 4.0 ) Pub Date : 2020-04-01 , DOI: 10.1109/lgrs.2019.2926530
Guoshuai Dong , Weimin Huang , William A. P. Smith , Peng Ren

We explore the use of convolutional neural networks (CNNs) for filling voids in digital elevation models (DEM). We propose a baseline approach using a fully convolutional network to predict complete from incomplete DEMs, which is trained in a supervised fashion. We then extend this to a shadow-constrained CNN (SCCNN) by introducing additional loss functions that encourage the restored DEM to adhere to geometric constraints implied by cast shadows. At the training time, we use automatically extracted cast shadow maps and known sun directions to compute the shadow-based supervisory signal in addition to the direct DEM supervision. At the test time, our network directly predicts restored DEMs from an incomplete DEM. One key advantage of our SCCNN model is that it is characterized by both CNN data inference and geometric shadow cues. It thus avoids data restoration that may violate shadowing conditions. Both our baseline CNN and SCCNN outperform the inverse distance weighting (IDW)-based interpolation method, with the shadow supervision enabling SCCNN to obtain the best performance.

中文翻译:

使用阴影约束卷积神经网络填充高程模型中的空隙

我们探索使用卷积神经网络 (CNN) 来填充数字高程模型 (DEM) 中的空白。我们提出了一种使用完全卷积网络从不完整的 DEM 中预测完整的基线方法,该方法以监督方式进行训练。然后,我们通过引入额外的损失函数将其扩展到阴影约束 CNN (SCCNN),这些损失函数鼓励恢复的 DEM 遵守投射阴影暗示的几何约束。在训练时,除了直接 DEM 监督之外,我们还使用自动提取的投射阴影图和已知的太阳方向来计算基于阴影的监督信号。在测试时,我们的网络直接从不完整的 DEM 中预测恢复的 DEM。我们的 SCCNN 模型的一个关键优势是它具有 CNN 数据推理和几何阴影线索的特点。因此,它避免了可能违反遮蔽条件的数据恢复。我们的基线 CNN 和 SCCNN 都优于基于反距离加权 (IDW) 的插值方法,阴影监督使 SCCNN 获得最佳性能。
更新日期:2020-04-01
down
wechat
bug