Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city's physical appearance and the behavior and health of its residents. Yet, the throughput of current methods is too limited to quantify the perception of cities across the world. To tackle this challenge, we introduce a new crowdsourced dataset containing 110,988 images from 56 cities, and 1,170,000 pairwise comparisons provided by 81,630 online volunteers along six perceptual attributes: safe, lively, boring, wealthy, depressing, and beautiful. Using this data, we train a Siamese-like convolutional neural architecture, which learns from a joint classification and ranking loss, to predict human judgments of pairwise image comparisons. Our results show that crowdsourcing combined with neural networks can produce urban perception data at the global scale.
CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations
Nanjing University（南京大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；SenseTime（商汤科技）；Shanghai Jiao Tong University（上海交通大学）；Beihang University（北京航空航天大学）
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Shanghai Jiao Tong University（上海交通大学）；National University of Singapore（新加坡国立大学）；Meituan（美团）；The Chinese University of Hong Kong（香港中文大学）；Shanghai University（上海大学）；University of Oxford（牛津大学）
A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
The State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University（武汉大学测绘遥感信息工程国家重点实验室）；School of Computer, Wuhan University（武汉大学计算机学院）
Urban precipitation downscaling using deep learning: a smart city application over Austin, Texas, USA
Jackson School of Geosciences（杰克逊地球科学学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；CIRES, University of Colorado Boulder（科罗拉多大学博尔德分校环境科学研究合作研究所）；NOAA/Physical Sciences Laboratory（美国国家海洋和大气管理局物理科学实验室）；Purdue University（普渡大学）；Cockrell School of Engineering（科克雷尔工程学院）
城市尺度缩减是将知识从较粗糙的气候信息转移到城市尺度评估的一个环节。这些高分辨率的评估需要过去数据和未来预测的多年气候学，使用传统的数值天气预测模型生成这些数据是复杂的，计算成本高。美国得克萨斯州奥斯汀市在过去十年中取得了巨大的发展。未来的系统规划需要高分辨率的城市规模数据集。在这项研究中，我们展示了一种新的方法，使用深度学习来生成一个通用操作符来执行城市降尺度。该算法在美国德克萨斯州奥斯汀市使用迭代超分辨率卷积神经网络（Iterative SRCNN）。我们展示了一个高分辨率的网格化降水产品（300米）从一个粗糙的（10公里）基于卫星的产品（JAXA GsMAP）的发展。高分辨率网格化的降水数据集提供了对过去大到小降水事件空间发布分布的深入了解。该算法在平均峰值信噪比和互信息方面有所改善，相对于三次插值基线，该算法可以生成尺寸为300 m X 300 m的高分辨率网格积。我们的研究结果对开发高分辨率网格化降水城市数据集以及未来针对其他城市和其他气候变量的智能城市规划具有重要意义。
