当前位置: X-MOL 学术ISPRS Int. J. Geo-Inf. › 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.)
Exploring the Potential of Deep Learning Segmentation for Mountain Roads Generalisation
ISPRS International Journal of Geo-Information ( IF 2.8 ) Pub Date : 2020-05-25 , DOI: 10.3390/ijgi9050338
Azelle Courtial , Achraf El Ayedi , Guillaume Touya , Xiang Zhang

Among cartographic generalisation problems, the generalisation of sinuous bends in mountain roads has always been a popular one due to its difficulty. Recent research showed the potential of deep learning techniques to overcome some remaining research problems regarding the automation of cartographic generalisation. This paper explores this potential on the popular mountain road generalisation problem, which requires smoothing the road, enlarging the bend summits, and schematising the bend series by removing some of the bends. We modelled the mountain road generalisation as a deep learning problem by generating an image from input vector road data, and tried to generate it as an output of the model a new image of the generalised roads. Similarly to previous studies on building generalisation, we used a U-Net architecture to generate the generalised image from the ungeneralised image. The deep learning model was trained and evaluated on a dataset composed of roads in the Alps extracted from IGN (the French national mapping agency) maps at 1:250,000 (output) and 1:25,000 (input) scale. The results are encouraging as the output image looks like a generalised version of the roads and the accuracy of pixel segmentation is around 65%. The model learns how to smooth the output roads, and that it needs to displace and enlarge symbols but does not always correctly achieve these operations. This article shows the ability of deep learning to understand and manage the geographic information for generalisation, but also highlights challenges to come.

中文翻译:

探索深度学习细分在山区道路推广中的潜力

在制图一般化问题中,由于其难度,山路中的弯曲弯道的一般化一直很受欢迎。最近的研究表明,深度学习技术有可能克服一些有关制图自动化的遗留问题。本文探讨了在流行的山区道路泛化问题上的潜力,该问题需要对道路进行平整处理,扩大弯道顶点和通过去除一些弯道来图解弯道系列。我们通过根据输入的矢量道路数据生成图像,将山区道路泛化建模为深度学习问题,并尝试将其生成为模型的输出,作为广义道路的新图像。与先前有关建筑物概化的研究类似,我们使用了U-Net架构,从非广义图像生成广义图像。对深度学习模型进行了训练和评估,该数据集由从IGN(法国国家地图局)地图中提取的阿尔卑斯山中的道路组成,比例为1:250,000(输出)和1:25,000(输入)。结果令人鼓舞,因为输出图像看起来像道路的通用版本,并且像素分割的准确性约为65%。该模型学习如何平滑输出道路,需要位移和放大符号,但并不总是能够正确实现这些操作。本文展示了深度学习理解和管理地理信息以进行概括的能力,但同时也强调了未来的挑战。对深度学习模型进行了训练和评估,该数据集由从IGN(法国国家地图局)地图中提取的阿尔卑斯山中的道路组成,比例为1:250,000(输出)和1:25,000(输入)。结果令人鼓舞,因为输出图像看起来像道路的通用版本,并且像素分割的准确性约为65%。该模型学习如何平滑输出道路,需要位移和放大符号,但并不总是能够正确实现这些操作。本文展示了深度学习理解和管理地理信息以进行概括的能力,但同时也强调了未来的挑战。对深度学习模型进行了训练和评估,该数据集由从IGN(法国国家地图局)地图中提取的阿尔卑斯山中的道路组成,比例为1:250,000(输出)和1:25,000(输入)。结果令人鼓舞,因为输出图像看起来像道路的通用版本,并且像素分割的准确性约为65%。该模型学习如何平滑输出道路,需要位移和放大符号,但并不总是能够正确实现这些操作。本文展示了深度学习理解和管理地理信息以进行概括的能力,但同时也强调了未来的挑战。结果令人鼓舞,因为输出图像看起来像道路的通用版本,并且像素分割的准确性约为65%。该模型学习如何平滑输出道路,需要位移和放大符号,但并不总是能够正确实现这些操作。本文展示了深度学习理解和管理地理信息以进行概括的能力,但同时也强调了未来的挑战。结果令人鼓舞,因为输出图像看起来像道路的通用版本,并且像素分割的准确性约为65%。该模型学习如何平滑输出道路,需要位移和放大符号,但并不总是能够正确实现这些操作。本文展示了深度学习理解和管理地理信息以进行概括的能力,但同时也强调了未来的挑战。
更新日期:2020-05-25
down
wechat
bug