CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials
CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials
复制标题
DOI：
10.1016/j.scs.2021.103630
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Maryam Hosseini;Fábio Miranda;Jianzhe Lin;Cláudio T. Silva
中科院分区：
文献类型：
--
作者：
Maryam Hosseini;Fábio Miranda;Jianzhe Lin;Cláudio T. Silva
虽然世界各地越来越多地提倡设计可持续和有弹性的城市建筑环境，但巨大的数据差距使得对紧迫的可持续发展问题的研究难以开展。众所周知，人行道具有强烈的经济和环境影响；然而，由于数据收集成本高昂且耗时，大多数城市缺乏其表面的空间目录。计算机视觉的最新进展以及街道级图像的可用性为城市提供了以更低的实施成本和更高的准确性提取大规模建筑环境数据的新机会。在本文中，我们提出了 CitySurfaces，这是一种基于主动学习的框架，它利用计算机视觉技术，使用广泛可用的街道图像对人行道材料进行分类。我们使用纽约市和波士顿的图像对框架进行了训练，评估结果显示 90.5% 的 mIoU 分数。此外，我们使用来自六个不同城市的图像评估了该框架，证明它可以应用于具有不同城市结构的区域，甚至可以应用于训练数据范围之外。 CitySurfaces 可以为研究人员和城市机构提供一种低成本、准确且可扩展的方法来收集人行道材料数据，这在解决气候变化和地表水管理等重大可持续发展问题方面发挥着关键作用。
While designing sustainable and resilient urban built environment is increasingly promoted around the world, significant data gaps have made research on pressing sustainability issues challenging to carry out. Pavements are known to have strong economic and environmental impacts; however, most cities lack a spatial catalog of their surfaces due to the cost-prohibitive and time-consuming nature of data collection. Recent advancements in computer vision, together with the availability of street-level images, provide new opportunities for cities to extract large-scale built environment data with lower implementation costs and higher accuracy. In this paper, we propose CitySurfaces, an active learning-based framework that leverages computer vision techniques for classifying sidewalk materials using widely available street-level images. We trained the framework on images from New York City and Boston and the evaluation results show a 90.5% mIoU score. Furthermore, we evaluated the framework using images from six different cities, demonstrating that it can be applied to regions with distinct urban fabrics, even outside the domain of the training data. CitySurfaces can provide researchers and city agencies with a low-cost, accurate, and extensible method to collect sidewalk material data which plays a critical role in addressing major sustainability issues, including climate change and surface water management.