Characterisation of urban environment and activity across space and time using street images and deep learning in Accra.
Characterisation of urban environment and activity across space and time using street images and deep learning in Accra.
复制标题
DOI：
10.1038/s41598-022-24474-1
复制
发表时间：
2022-11-28
影响因子：
4.6
通讯作者：
Ezzati, Majid
中科院分区：
文献类型：
--
作者：
Nathvani, Ricky;Clark, Sierra N.;Muller, Emily;Alli, Abosede S.;Bennett, James E.;Nimo, James;Moses, Josephine Bedford;Baah, Solomon;Metzler, A. Barbara;Brauer, Michael;Suel, Esra;Hughes, Allison F.;Rashid, Theo;Gemmell, Emily;Moulds, Simon;Baumgartner, Jill;Toledano, Mireille;Agyemang, Ernest;Owusu, George;Agyei-Mensah, Samuel;Arku, Raphael E.;Ezzati, Majid
城市环境影响着人类的健康、安全和福祉。非洲城市的增长速度快于其他地区，但用于指导城市规划和政策的数据有限。我们的目标是使用智能传感和分析来描述与健康、宜居性、安全性和可持续性相关的城市环境特征的空间模式和时间动态。我们在加纳首都阿克拉的145个代表性地点收集了210万张延时白天和黑夜图像的新数据集。我们为20个上下文相关的对象手动标记了1250个图像子集，并使用迁移学习和数据增强来重新训练卷积神经网络，以在剩余的图像中检测它们。我们确定了2350万个这些物体的实例，其中包括966万个人（占所有物体的41%），其次是汽车（419万，18%），雨伞（300万，13%）和被称为tro tros的非正式运营的小巴（294万，13%）。人、大型车辆和与市场有关的物品在商业核心和人口密集的非正式社区最为常见，而垃圾和动物在外围地区最为常见。在人口密集的定居点，物体的日变化最小，在商业中心，物体的日变化最大。我们的新数据和方法表明，智能传感和分析可以为规划和政策决策提供信息，使城市更宜居、公平、可持续和健康。
The urban environment influences human health, safety and wellbeing. Cities in Africa are growing faster than other regions but have limited data to guide urban planning and policies. Our aim was to use smart sensing and analytics to characterise the spatial patterns and temporal dynamics of features of the urban environment relevant for health, liveability, safety and sustainability. We collected a novel dataset of 2.1 million time-lapsed day and night images at 145 representative locations throughout the Metropolis of Accra, Ghana. We manually labelled a subset of 1,250 images for 20 contextually relevant objects and used transfer learning with data augmentation to retrain a convolutional neural network to detect them in the remaining images. We identified 23.5 million instances of these objects including 9.66 million instances of persons (41% of all objects), followed by cars (4.19 million, 18%), umbrellas (3.00 million, 13%), and informally operated minibuses known as tro tros (2.94 million, 13%). People, large vehicles and market-related objects were most common in the commercial core and densely populated informal neighbourhoods, while refuse and animals were most observed in the peripheries. The daily variability of objects was smallest in densely populated settlements and largest in the commercial centre. Our novel data and methodology shows that smart sensing and analytics can inform planning and policy decisions for making cities more liveable, equitable, sustainable and healthy.
登录
查看更多内容
DOI：
10.1088/1748-9326/ac074a
发表时间：
2021-07
期刊：
Environmental research letters : ERL [Web site]
影响因子：
--
作者：
Alli AS;Clark SN;Hughes A;Nimo J;Bedford-Moses J;Baah S;Wang J;Vallarino J;Agyemang E;Barratt B;Beddows A;Kelly F;Owusu G;Baumgartner J;Brauer M;Ezzati M;Agyei-Mensah S;Arku RE
通讯作者：
Arku RE
影响因子：
2.9
作者：
Bixby H;Bennett JE;Bawah AA;Arku RE;Annim SK;Anum JD;Mintah SE;Schmidt AM;Agyei-Asabere C;Robinson BE;Cavanaugh A;Agyei-Mensah S;Owusu G;Ezzati M;Baumgartner J
通讯作者：
Baumgartner J
影响因子：
4.7
作者：
Brown, Alison;Lyons, Michal;Dankoco, Ibrahima
通讯作者：
Dankoco, Ibrahima
DOI：
10.1016/j.trf.2016.09.033
发表时间：
2017-04-01
影响因子：
4.1
作者：
Birago, Dora;Mensah, Seth Opoku;Sharma, Somesh
通讯作者：
Sharma, Somesh
DOI：
10.1016/j.compenvurbsys.2019.101350
发表时间：
2019-09-01
影响因子：
6.8
作者：
Campbell, Andrew;Both, Alan;Sun, Qian (Chayn)
通讯作者：
Sun, Qian (Chayn)