ABSTRACT

In this study, we present a new automatic deep learning-based network named Road Vectorization Network (RoadVecNet), which comprises interlinked UNet networks to simultaneously perform road segmentation and road vectorization. Particularly, RoadVecNet contains two UNet networks. The first network with powerful representation capability can obtain more coherent and satisfactory road segmentation maps even under a complex urban set-up. The second network is linked to the first network to vectorize road networks by utilizing all of the previously generated feature maps. We utilize a loss function called focal loss weighted by median frequency balancing (MFB_FL) to focus on the hard samples, fix the training data imbalance problem, and improve the road extraction and vectorization performance. A new module named dense dilated spatial pyramid pooling, which combines the benefit of cascaded modules with atrous convolution and atrous spatial pyramid pooling, is designed to produce more scale features over a broader range. Two types of high-resolution remote sensing datasets, namely, aerial and Google Earth imagery, were used for road segmentation and road vectorization tasks. Classification results indicate that the RoadVecNet outperforms the state-of-the-art deep learning-based networks with 92.51% and 93.40% F1 score for road surface segmentation and 89.24% and 92.41% F1 score for road vectorization from the aerial and Google Earth road datasets, respectively. In addition, the proposed method outperforms the other comparative methods in terms of qualitative results and produces high-resolution road segmentation and vectorization maps. As a conclusion, the presented method demonstrates that considering topological quality may result in improvement of the final road network, which is essential in various applications, such as GIS database updating.

摘要

在这项研究中，我们提出了一种新的基于深度学习的自动网络，称为道路矢量化网络 (RoadVecNet)，该网络由相互关联的 UNet 网络组成，可同时执行道路分割和道路矢量化。特别是 RoadVecNet 包含两个 UNet 网络。即使在复杂的城市设置下，具有强大表示能力的第一个网络也可以获得更连贯和令人满意的道路分割图。第二个网络连接到第一个网络，通过利用所有先前生成的特征图对道路网络进行矢量化。我们利用称为中频平衡加权的焦点损失（MFB_FL）的损失函数来关注硬样本，修复训练数据不平衡问题，并提高道路提取和矢量化性能。一个名为密集扩张空间金字塔池化的新模块，它将级联模块的优点与多孔卷积和多孔空间金字塔池化相结合，旨在在更广的范围内产生更多的尺度特征。两种类型的高分辨率遥感数据集，即航空和谷歌地球图像，用于道路分割和道路矢量化任务。分类结果表明，RoadVecNet 以 92.51% 和 93.40% 的道路表面分割 F1 分数和 89.24% 和 92.41% 的 F1 分数在来自空中和谷歌地球道路的道路矢量化方面优于最先进的基于深度学习的网络数据集，分别。此外，所提出的方法在定性结果方面优于其他比较方法，并产生高分辨率的道路分割和矢量化地图。作为结论，