Fang Zhiguo, Liu Cong, Xiao Yu, Jin Chenghao, Zhuang Xinjia

Keywords： Shanghai Street; Street Aesthetics; Street View Image; Deep Learning; Multi-source Data

Abstract：

It is crucial to create an aesthetic street space that combines traffic function and pedestrian space perception through the environment, and supports social behavior to realize the transformation of the transportation development model. However, street aesthetic assessment and analysis are limited due to insufficient technology and availability of data sources. The emergence of data such as map points of interest (POI), street view images, and three-dimensional building maps has provided a large number of new images and data support for the street space research, breaking the limitations of data sources. This paper takes Shanghai street space as the research object, based on deep learning and GIS, using multi-source data as the carrier to conduct large-scale streetscape aesthetic evaluation and measurement of four types of object indicators: street physical space, ground floor interface, greening facility, and the macroscopic morphology. On this basis, the relationship between the object indicators and the street aesthetic assessment is revealed through mathematical derivation. It finds that physical space has the greatest influence on the perception of individuals in the three-dimensional relationship of streets; the green viewing rate is a key factor affecting the perception of street aesthetics; the street width has a greater impact on the aesthetic perception than the aspect ratio; the number of storefront signboards and building density also have a positive impact on the aesthetic evaluation. This paper can provide a basis for optimizing the spatial layout of streets, scientific and rational support for creating walkable cities and healthy cities, and practical support for optimizing the built environment in related disciplines.

Funds：

• [1] JACOBS J. The death and life of great American cities[M]. New York: Vintage, 2016.

  [2] GEHL J. Life between buildings: using public space[M]. New York: Van Nostrand Reinhold, 1987.

  [3] WHYTE W H. The social life of small urban spaces[M]. Washington, DC: Conservation Foundation, 1980.

  [4] LYNCH K. Good city form[M]. Cambridge: MIT Press, 1984.

  [5] MONTGOMERY J. Making a city: urbanity, vitality and urban design[J]. Journal of urban design, 1998, 3(1): 93-116.

  [6] HERBERT D, DAVIDSON N. Modifying the built environment: the impact of improved street lighting[J]. Geoforum, 1994(25): 339-350.

  [7] LILLEBYE E. Architectural and functional relationships in street planning: an historical view[J]. Landscape and urban planning, 1996(35): 85-105.

  [8] AMIR S, MISGAV A. A framework for street tree planning in urban areas in Israel[J]. Landscape and urban planning, 1990, 19(3): 203-212.

  [9] REHAN R M. Sustainable streetscape as an effective tool in sustainable urban design[J]. HBRC Journal, 2013, 9(2): 173-186.

  [10] 王德, 张昀, 崔昆仑. 基于SD 法的城市感知研究——以浙江台州地区为例[J]. 地理研究, 2009, 28(6): 1528-1536.

  [11] 谭少华, 韩玲. 城市街道美景影响因素分析——以重庆市的三条街道为例[J]. 城市问题, 2015(2): 43-49.

  [12] YE Y, ZENG W, SHEN Q, et al. The visual quality of streets: a humancentred continuous measurement based on machine learning algorithms and street view images[J]. Environment and planning b: urban analytics and city science, 2019, 46(8): 1439-1457.

  [13] MIDDEL A, LUKASCZYK J, ZAKRZEWSKI S, et al. Urban form and composition of street canyons: a human-centric big data and deep learning approach[J]. Landscape and urban planning, 2019, 183: 122-132.

  [14] CAMPBELL A, BOTH A, SUN Q C. Detecting and mapping traffic signs from Google Street View images using deep learning and GIS[J]. Computers, environment and urban systems, 2019, 77: 101350.

  [15] HU C, ZHANG F, GONG F, et al. Classification and mapping of urban canyon geometry using Google Street View images and deep multitask learning[J]. Building and environment, 2020(167): 106424.

  [16] 邵源, 叶丹, 叶宇. 基于街景数据和深度学习的街道界面渗透率大规模测度研究——以上海为例[J/OL]. 国际城市规划, 2022[2022-12-25]. DOI: 10.19830/j.upi.2021.241.

  [17] HARVEY C, AULTMAN L, TROY A, et al. Effects of skeletal streetscape design on perceived safety[J]. Landscape and urban planning, 2015, 142: 18-28.

  [18] SHEN Y, KARIMI K. Urban function connectivity: characterisation of functional urban streets with social media check-in data[J]. Cities, 2016(55): 9-21.

  [19] SALESSES P, SCHEECHETNER K, HIDALGO C A, et al. The collaborative image of the city: mapping the inequality of urban perception[J]. PLoS One, 2013, 8(7): e68400.

  [20] NAIK N, P HILIPOOM J, RASKAR R, et al. Streetscore-predicting the perceived safety of one million streetscapes[C] // Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2014: 779-785.

  [21] ZHANG F, ZHOU B, LIU L, et al. Measuring human perceptions of a largescale urban region using machine learning[J]. GeoJournal, 2018, 180: 148-160.

  [22] LIU L, SILVA E A, WU C, et al. A machine learning-based method for the large-scale evaluation of the qualities of the urban environment[J]. Computers, environment and urban systems, 2017, 65: 113-125.

  [23] WANG R, LU Y, ZHANG J, et al. The relationship between visual enclosure for neighbourhood street walkability and elders’ mental health in China: using street view images[J]. Journal of transport & health, 2019, 13: 90-102.

  [24] WANG R, LIU Y, LU Y, et al. Perceptions of built environment and health outcomes for older Chinese in Beijing: a big data approach with street view images and deep learning technique[J]. Computers, environment and urban systems, 2019, 78: 101386.

  [25] 诺伯舒兹. 场所精神——迈向建筑现象学[M]. 施植明, 译. 武汉: 华中科技大学出版社，2010.

  [26] JANSSON M, FORS H, LINDGREN T, et al. Perceived personal safety in relation to urban woodland vegetation–a review[J]. Urban forestry & urban green, 2013(2): 127-133.

  [27] GEHL J, KAEFER L J, REIGSTAD S. Close encounters with buildings[J]. Urban design international, 2006, 11(1): 29-47.

  [28] COHEN L E, FELSON M. Social change and crime rate trends: a routine activities approach[J]. American sociological review, 1979(4): 588-608.

  [29] 周钰. 街道界面形态的量化研究[M]. 北京: 中国建筑工业出版社, 2018.

  [30] 奚婷霞, 匡晓明, 朱弋宇, 等. 基于人感知维度的街道更新设计引导探索——以上海市静安区彭浦镇美丽街区更新改造为例[J]. 城市规划学刊, 2019( 增刊1): 168-176.

  [31] SALESSES P, SCHECHTNER K, HIDALGO C A. The collaborative image of the city: mapping the inequality of urban perception[J]. PLoS one, 2013, 8(7): e68400.

  [32] ASHIHARA Y. The aesthetic townscape[M]. Cambridge, MA: The MIT press, 1983.

  [33] 阿兰·B. 雅各布斯. 伟大的街道[M]. 王又佳, 金秋野, 译. 北京: 中国建筑工业出版社, 2009.

  [34] City of Melbourne. Places for people: Melbourne[R]. City of Melbourne, 2004.

  [35] CARMONA M, HEATH T, Oc T, et al. Public places, urban spaces: the dimensions of urban design[M]. Kidlington: Architectural Press, 2003.

  [36] JIANG B, MAK C N S, ZHONG H, et al. From broken windows to perceived routine activities: examining impacts of environmental interventions on perceived safety of urban alleys[J]. Frontiers in psychology, 2018(9): 2450.

  [37] 徐磊青, 孟若希, 陈筝. 迷人的街道：建筑界面与绿视率的影响[J]. 风景园林, 2017(10): 27-33.

  [38] 金慧, 罗川西, 金荷仙. 城市公园绿视率对人体身心健康的影响——以杭州为例[J]. 南方建筑, 2022(6): 43-51.