Public space quality is a multidimensional concept. Urban design quality and physical disorder represent it from the perspectives of design and maintenance, respectively. However, the practical relationship between these two factors remains unclear, raising questions about the necessity of measuring multiple dimensions of public space quality simultaneously. Based on classical studies and theories, this study developed index systems for both factors. Utilizing artificial virtual auditing and deep learning models, including FCN and SegNet, the street visual quality of two Chinese cities was assessed from the perspectives of urban design and physical disorder using extensive street view images. The correlation between these two factors was explored. The results showed that the Spearman correlation coefficients for urban design quality and physical disorder were 0.308 and −0.085 in the two cities, respectively, indicating weak or unclear correlations. Additionally, the fit and explanatory power of the linear and nonlinear regression models constructed were poor, further demonstrating that it is difficult to predict and explain one variable using the other. In the robustness test, the results were further validated by including control variables related to urban vitality, cultural characteristics, and urban development, considering the impact of the distribution of the street view images, drilling down to more granular dimensions and extending the scope of the study to a wider area. The levels of design and maintenance of streets cannot be conflated or substituted, and neither can independently represent the overall space quality alone. Both are indispensable, making it crucial to separately assess and address space quality issues from different perspectives. These results broaden our understanding of high-visual-quality street space and provide references for urban planners and stakeholders in improving street space quality.
Abu-GhazzehTM (1997) Signs, advertising and the imageability of buildings: a perceptual selection in the view from the street in Amman, Jordan. Habitat International21(2): 255–267.
BadrinarayananVKendallACipollaR (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence39(12): 2481–2495.
5.
BiljeckiFItoK (2021) Street view imagery in urban analytics and GIS: a review. Landscape and Urban Planning215: 104217.
ChenSBiljeckiF (2023) Automatic assessment of public open spaces using street view imagery. Cities137: 104329.
8.
ChenJChenLLiY, et al. (2023) Measuring physical disorder in urban street spaces: a large-scale analysis using street view images and deep learning. Annals of the Association of American Geographers113(2): 469–487.
9.
DingCCaoXLiuC (2019) How does the station-area built environment influence metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds. Journal of Transport Geography77: 70–78.
10.
EwingRHandyS (2009) Measuring the unmeasurable: urban design qualities related to walkability. Journal of Urban Design14(1): 65–84.
11.
EwingRHandySBrownsonRC, et al. (2006) Identifying and measuring urban design qualities related to walkability. Journal of Physical Activity and Health3(s1): S223–S240.
12.
FanZZhangFLooBPY, et al. (2023) Urban visual intelligence: uncovering hidden city profiles with street view images. Proceedings of the National Academy of Sciences120(27): e2220417120.
13.
FranziniLCaughyMONettlesSM, et al. (2008) Perceptions of disorder: contributions of neighborhood characteristics to subjective perceptions of disorder. Journal of Environmental Psychology28(1): 83–93.
14.
GehlJ (1987) Life between Buidlings. Using Public Space. New York: Van Nostrand Reinhold.
15.
GrubesicTHWallaceDChamberlainAW, et al. (2018) Using unmanned aerial systems (UAS) for remotely sensing physical disorder in neighborhoods. Landscape and Urban Planning169: 148–159.
16.
GullonPFryDPlascakJJ, et al. (2023) Measuring changes in neighborhood disorder using Google street view longitudinal imagery: a feasibility study. Cities & Health7(5): 823–829.
17.
HamidiSMoazzeniS (2019) Examining the relationship between urban design qualities and walking behavior: empirical evidence from Dallas, TX. Sustainability11(10): 2720.
18.
HamidiSBonakdarAKeshavarziG, et al. (2020) Do urban design qualities add to property values? An empirical analysis of the relationship between urban design qualities and property values. Cities98: 102564.
19.
HandySLBoarnetMGEwingR, et al. (2002) How the built environment affects physical activity: views from urban planning. American Journal of Preventive Medicine23(2): 64–73.
20.
HatamiFRahmanMMNikparvarB, et al. (2023) Non-linear associations between the urban built environment and commuting modal split: a random forest approach and SHAP evaluation. IEEE Access11: 12649–12662.
21.
HeLPáezALiuD (2017) Built environment and violent crime: an environmental audit approach using Google Street View. Computers, Environment and Urban Systems66: 83–95.
22.
HoDCWLaiLWCWangA (2021) The effects of ‘publicness’ and quality of publicly accessible open space upon user satisfaction. Environment and Planning B: Urban Analytics and City Science48(4): 861–879.
23.
HooiEPojaniD (2020) Urban design quality and walkability: an audit of suburban high streets in an Australian city. Journal of Urban Design25(1): 155–179.
24.
HsuWZhangYLongY (2022) Valuing the micropublic space: a perspective from Beijing housing prices. Journal of Urban Planning and Development148(2): 04022012.
25.
HuCJiaSZhangF, et al. (2023) UPD explainer: an interpretable transformer-based framework for urban physical disorder detection using street view imagery. ISPRS Journal of Photogrammetry and Remote Sensing204: 209–222.
26.
JiaJZhangXHuangC, et al. (2022) Multiscale analysis of human social sensing of urban appearance and its effects on house price appreciation in Wuhan, China. Sustainable Cities and Society81: 103844.
27.
JiangYZhangYLiuY, et al. (2023) A review of urban vitality research in the Chinese world. Transactions in Urban Data, Science, and Technology2(2–3): 81–99.
28.
KohliDSliuzasRSteinA (2016) Urban slum detection using texture and spatial metrics derived from satellite imagery. Journal of Spatial Science61(2): 405–426.
29.
KooBWHwangUGuhathakurtaS (2023) Streetscapes as part of servicescapes: can walkable streetscapes make local businesses more attractive?Computers, Environment and Urban Systems106: 102030.
30.
KronkvistK (2013) Systematic social observation of physical disorder in inner-city urban neighborhoods through google street view: the correlation between virtually observed physical disorder, self-reported disorder and victimization of property crimes. Malmö högskola/Hälsa och samhälle, Available at: https://www.diva-portal.org/smash/record.jsf?pid=diva2:1487138accessed 14 May 2024.
31.
KufferMPfefferKSliuzasR (2016) Slums from space—15 years of slum mapping using remote sensing. Remote Sensing8(6): 455.
32.
LiYLongY (2024) Inferring storefront vacancy using mobile sensing images and computer vision approaches. Computers, Environment and Urban Systems108: 102071.
33.
LiYMaYLongY (2024) Protocol for assessing neighborhood physical disorder using the YOLOv8 deep learning model. STAR protocols5(1): 102778.
34.
LiYPengLWuC, et al. (2022a) Street view imagery (SVI) in the built environment: a theoretical and systematic review. Buildings12(8): 1167.
35.
LiSMaSTongD, et al. (2022b) Associations between the quality of street space and the attributes of the built environment using large volumes of street view pictures. Environment and Planning B: Urban Analytics and City Science49(4): 1197–1211.
36.
LiWLongYKwanM-P, et al. (2022c) Measuring individuals’ mobility-based exposure to neighborhood physical disorder with wearable cameras. Applied Geography145: 102728.
37.
LiuLSilvaEAWuC, et al. (2017) A machine learning-based method for the large-scale evaluation of the qualities of the urban environment. Computers, Environment and Urban Systems65: 113–125.
38.
LongYLiuL (2017) How green are the streets? An analysis for central areas of Chinese cities using tencent street view. PLoS One12(2): e0171110.
39.
LongYZhangE (2024) City laboratory: embracing new data, new elements, and new pathways to invent new cities. Environment and Planning B: Urban Analytics and City Science51(5): 1068–1072.
MarcoMGraciaEMartín-FernándezM, et al. (2017) Validation of a Google street view-based neighborhood disorder observational scale. Journal of Urban Health94(2): 190–198.
NasarJL (1990) The evaluative image of the city. Journal of the American Planning Association56(1): 41–53.
44.
OdgersCLCaspiABatesCJ, et al. (2012) Systematic social observation of children’s neighborhoods using Google street view: a reliable and cost‐effective method. Journal of Child Psychology and Psychiatry53(10): 1009–1017.
45.
ParsaABMovahediATaghipourH, et al. (2020) Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis. Accident Analysis & Prevention136: 105405.
46.
PlascakJJDesire-BrisardTMaysD, et al. (2023) Associations between observed neighborhood physical disorder and health behaviors, New Jersey behavioral risk factor Surveillance System 2011–2016. Preventive Medicine Reports32: 102131.
47.
QiuWLiWLiuX, et al. (2021) Subjectively measured streetscape perceptions to inform urban design strategies for Shanghai. ISPRS International Journal of Geo-Information10(8): 493.
48.
QuinnJWMooneySJSheehanDM, et al. (2016) Neighborhood physical disorder in New York City. Journal of Maps12(1): 53–60.
49.
RossCEMirowskyJ (1999) Disorder and decay: the concept and measurement of perceived neighborhood disorder. Urban Affairs Review34(3): 412–432.
50.
RundleAGBaderMDRichardsCA, et al. (2011) Using Google street view to audit neighborhood environments. American Journal of Preventive Medicine40(1): 94–100.
51.
SampsonRJRaudenbushSW (1999) Systematic social observation of public spaces: a new look at disorder in urban neighborhoods. American Journal of Sociology105(3): 603–651.
52.
SanoffH (2016) Visual Research Methods in Design (Routledge Revivals). Routledge.
53.
ShenQZengWYeY, et al. (2018) StreetVizor: visual exploration of human-scale urban forms based on street views. IEEE Transactions on Visualization and Computer Graphics24(1): 1004–1013.
54.
SnaphaanTHardynsW (2021) Utilizing geo-referenced imagery for systematic social observation of neighborhood disorder. Computers, Environment and Urban Systems90: 101691.
55.
SuNLiWQiuW (2023) Measuring the associations between eye-level urban design quality and on-street crime density around New York subway entrances. Habitat International131: 102728.
56.
SuelEPolakJWBennettJE, et al. (2019) Measuring social, environmental and health inequalities using deep learning and street imagery. Scientific Reports9(1): 6229.
57.
WanTLuWSunP (2022) Constructing the quality measurement model of street space and its application in the old town in Wuhan. Frontiers in Public Health10: 816317.
58.
WongRWangY (2022) Role of neighborhood physical disorder and social cohesion on racial and ethnic disparities in dementia risk. Journal of Aging and Health34(9–10): 1178–1187.
59.
XuTTaNChaiY, et al. (2024) Complex associations between multidimensional land use mix and walking: walk more or farther?Transactions in Urban Data, Science, and Technology3(1–2): 3–30.
60.
YeYZengWShenQ, et al. (2019) The visual quality of streets: a human-centred continuous measurement based on machine learning algorithms and street view images. Environment and Planning B: Urban Analytics and City Science46(8): 1439–1457.
61.
YinL (2017) Street level urban design qualities for walkability: combining 2D and 3D GIS measures. Computers, Environment and Urban Systems64: 288–296.
62.
ZhangEXieHLongY (2023a) Decoding the association between urban streetscape skeletons and urban activities: experiments in Beijing using Dazhong Dianping data. Transactions in Urban Data, Science, and Technology2(1): 3–18.
63.
ZhangFWegnerJDYangB, et al. (2023b) Street-level imagery analytics and applications. ISPRS Journal of Photogrammetry and Remote Sensing199: 195–196.
64.
ZhangYDengQGuoM, et al. (2023c) Using street view imagery to examine the association between urban neighborhood disorder and the long-term recurrence risk of patients discharged with acute myocardial infarction in central Beijing, China. Cities138: 104366.
65.
ZhangFSalazar-MirandaADuarteF, et al. (2024) Urban visual intelligence: studying cities with artificial intelligence and street-level imagery. Annals of the Association of American Geographers114: 876–897.
66.
ZhuWWangJQinB (2021) Quantity or quality? Exploring the association between public open space and mental health in urban China. Landscape and Urban Planning213: 104128.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
