Urban form and composition of street canyons: A human-centric big data and deep learning approach
Urban form and composition of street canyons: A human-centric big data and deep learning approach
复制标题
DOI：
10.1016/j.landurbplan.2018.12.001
复制
发表时间：
2019-03-01
影响因子：
9.1
通讯作者：
Maciejewski, Ross
中科院分区：
文献类型：
--
作者：
Middel, Ariane;Lukasczyk, Jonas;Maciejewski, Ross
各种研究应用需要详细的指标来描述城市的形式和组成，但由于数据可用性、质量和处理能力有限，参数计算仍然是一个挑战。我们开发了一种创新的大数据方法，从谷歌街景（GSV）图像中获得行人所经历的街道形态和城市特征组成。我们采用了一个可扩展的深度学习框架，将90度视场GSV图像立方体分割为六类：天空、树木、建筑物、不透水表面、透水表面和非永久性物体。我们通过区分三个视图方向（横向、向下和向上）和引入一个空类作为训练标签来提高分类精度。为了模拟行人在街道峡谷中感知到的城市环境，我们将分割的图像立方体投影到球体上，并评估球体上每个表面类别的比例。为了证明我们的方法的应用，我们使用堆叠面积图分析了费城县和三个费城社区（郊区、中心城市、低收入社区）的城市形态和组成。我们的方法完全可扩展到其他地理位置，并构成了构建全球形态数据库的重要一步，从以人为中心的角度描述城市的形式和组成。
Various research applications require detailed metrics to describe the form and composition of cities at fine scales, but the parameter computation remains a challenge due to limited data availability, quality, and processing capabilities. We developed an innovative big data approach to derive street-level morphology and urban feature composition as experienced by a pedestrian from Google Street View (GSV) imagery. We employed a scalable deep learning framework to segment 90-degree field of view GSV image cubes into six classes: sky, trees, buildings, impervious surfaces, pervious surfaces, and non-permanent objects. We increased the classification accuracy by differentiating between three view directions (lateral, down, and up) and by introducing a void class as training label. To model the urban environment as perceived by a pedestrian in a street canyon, we projected the segmented image cubes onto spheres and evaluated the fraction of each surface class on the sphere. To demonstrate the application of our approach, we analyzed the urban form and composition of Philadelphia County and three Philadelphia neighborhoods (suburb, center city, lower income neighborhood) using stacked area graphs. Our method is fully scalable to other geographic locations and constitutes an important step towards building a global morphological database to describe the form and composition of cities from a human-centric perspective.