当前位置: X-MOL 学术Int. J. Appl. Earth Obs. Geoinf. › 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.)
GA-Net: A geometry prior assisted neural network for road extraction
International Journal of Applied Earth Observation and Geoinformation ( IF 7.5 ) Pub Date : 2022-09-29 , DOI: 10.1016/j.jag.2022.103004
Xin Chen, Qun Sun, Wenyue Guo, Chunping Qiu, Anzhu Yu

With geospatial intelligence research developing rapidly, automatic road extraction is becoming a fundamental and challenging task. Due to the special geometric structure and spectral information of road networks, existing methods suffer from incomplete and fractured results. In this work, a novel road extraction convolutional neural network, incorporating the road boundary details and road junction information via a dual-branch multi-task structure, is proposed to learn synergistic feature representations and strengthen road connectivity. Firstly, a BiFPN-based feature aggregation module is utilised to bridge the semantic gap between low-level and high-level feature maps, allowing multi-scale spatial details to be fully fused. Secondly, the boundary auxiliary branch, using a U-shaped network with a spatial-channel attention module, captures residential information for the backbone to enhance the subtleties of road edges. Thirdly, the node inferring branch models the road junction position jointly with the road surface, aiming to strengthen the topology structure and reduce the fragmented road segments. We perform experiments on three diverse road datasets, namely the DeepGlobe dataset, Massachusetts dataset, and SpaceNet dataset. The results demonstrate that our model shows an overall performance improvement over some SOTA algorithms and the IoU indicator achieves 3.86%, 0.79%, and 1.71% improvements over Unet on the three datasets, respectively.



中文翻译:

GA-Net:用于道路提取的几何先验辅助神经网络

随着地理空间情报研究的快速发展,自动道路提取正成为一项基础性且具有挑战性的任务。由于道路网络的特殊几何结构和光谱信息,现有方法存在不完整和断裂的结果。在这项工作中,提出了一种新颖的道路提取卷积神经网络,通过双分支多任务结构结合道路边界细节和道路交叉口信息,以学习协同特征表示并增强道路连通性。首先,利用基于 BiFPN 的特征聚合模块来弥合低层和高层特征图之间的语义鸿沟,使多尺度空间细节得到充分融合。其次,边界辅助分支,使用带有空间通道注意力模块的 U 形网络,为主干捕获住宅信息,以增强道路边缘的微妙之处。第三,节点推断分支与路面联合建模道路交叉口位置,旨在加强拓扑结构并减少碎片化路段。我们在三个不同的道路数据集上进行实验,即 DeepGlobe 数据集、Massachusetts 数据集和 SpaceNet 数据集。结果表明,我们的模型显示出比某些 SOTA 算法的整体性能提高,并且 IoU 指标在三个数据集上分别比 Unet 提高了 3.86%、0.79% 和 1.71%。旨在加强拓扑结构并减少支离破碎的路段。我们在三个不同的道路数据集上进行实验,即 DeepGlobe 数据集、Massachusetts 数据集和 SpaceNet 数据集。结果表明,我们的模型显示出比某些 SOTA 算法的整体性能提高,并且 IoU 指标在三个数据集上分别比 Unet 提高了 3.86%、0.79% 和 1.71%。旨在加强拓扑结构并减少支离破碎的路段。我们在三个不同的道路数据集上进行实验,即 DeepGlobe 数据集、Massachusetts 数据集和 SpaceNet 数据集。结果表明,我们的模型显示出比某些 SOTA 算法的整体性能提高,并且 IoU 指标在三个数据集上分别比 Unet 提高了 3.86%、0.79% 和 1.71%。

更新日期:2022-09-30
down
wechat
bug