Redlining, institutionalized by the HOLC in the 1930s, was a discriminatory credit mapping system that divided residential areas into A–D grades based on neighborhood conditions. Although long abolished, its unequal impacts persist. Previous studies mainly focused on racial and socioeconomic inequalities, while this study used street view image analysis to examine how redlining has produced inequalities in Visual Perceptual Quality through differences in the built environment. Taking Buffalo as a case, this study applied computer vision and machine learning with the Place Pulse 2.0 dataset to predict six perceptual dimensions—beauty, safety, wealth, liveliness, boring, and depressing. The results reveal significant differences in perception scores across redlining grades, indicating that inequality persists at the perceptual level. SHAP analysis further shows that these disparities are mainly driven by built environment features like trees, buildings, and roads. The uneven distribution of these key features across redlining grades forms the physical basis of perceptual inequality. The study also discussed the relationship between such inequality and the long-term planning bias and uneven investment shaped by redlining. This study expands the research scope of redlining and provides quantitative evidence for improving disadvantaged neighborhoods long affected by its legacy.
AaronsonDHartleyDMazumderB (2021) The effects of the 1930s HOLC “redlining” maps. American Economic Journal: Economic Policy13(4): 355–392. https://doi.org/10.1257/pol.20190414
2.
AbdiHWilliamsLJ (2010) Tukey’s honestly significant difference (HSD) test. Encyclopedia of Research Design3(1): 1–5.
BurkeLMSchwalbachJ (2021) Housing redlining and its lingering effects on education opportunity. Backgrounder. No. 3594. Heritage Foundation.
7.
ChengLChuSZongW, et al. (2017) Use of tencent street view imagery for visual perception of streets. ISPRS International Journal of Geo-Information6(9): 265. https://doi.org/10.3390/ijgi6090265
8.
ChiangY-CLiuH-HLiD, et al. (2023) Quantification through deep learning of sky view factor and greenery on urban streets during hot and cool seasons. Landscape and Urban Planning232: 104679. https://doi.org/10.1016/j.landurbplan.2022.104679
DubeyANaikNParikhD, et al. (2016) Deep learning the city: quantifying urban perception at a global scale. In: European Conference on Computer Vision. Springer, pp. 196–212.
FanZFengC-CBiljeckiF (2025) Coverage and bias of street view imagery in mapping the urban environment. Computers, Environment and Urban Systems117: 102253. https://doi.org/10.1016/j.compenvurbsys.2025.102253
14.
FosterSGiles-CortiB (2008) The built environment, neighborhood crime and constrained physical activity: an exploration of inconsistent findings. Preventive Medicine47(3): 241–251. https://doi.org/10.1016/j.ypmed.2008.03.017
15.
GelorminoEMelisGMariettaC, et al. (2015) From built environment to health inequalities: an explanatory framework based on evidence. Preventive Medicine Reports2: 737–745. https://doi.org/10.1016/j.pmedr.2015.08.019
16.
GibbonsJ (2023) Examining the long-term influence of new deal era redlining on contemporary gentrification. Urban Studies60(14): 2816–2834. https://doi.org/10.1177/00420980231160469
17.
HanYZhongTYehAG, et al. (2023) Mapping seasonal changes of street greenery using multi-temporal street-view images. Sustainable Cities and Society92: 104498. https://doi.org/10.1016/j.scs.2023.104498
18.
HeKGkioxariGDollárP, et al. (2017) Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, Venice, Italy, 22–29 October 2017, pp. 2961–2969.
LiXZhangCLiW (2015) Does the visibility of greenery increase perceived safety in urban areas? Evidence from the place pulse 1.0 dataset. ISPRS International Journal of Geo-Information4(3): 1166–1183. https://doi.org/10.3390/ijgi4031166
23.
LiYLuJMengY, et al. (2025) Exploring urban spatial quality through street view imagery and human perception analysis. Buildings15(17): 3116. https://doi.org/10.3390/buildings15173116
24.
LiangJGongJSunJ, et al. (2017) Automatic sky view factor estimation from street view photographs—A big data approach. Remote Sensing9(5): 411. https://doi.org/10.3390/rs9050411
25.
LiuYChenMWangM, et al. (2023) An interpretable machine learning framework for measuring urban perceptions from panoramic street view images. iScience26(3): 106132. https://doi.org/10.1016/j.isci.2023.106132
26.
LouSStancatoGBoffiM, et al. (2024) Evaluating urban perception: comparing place pulse 2.0 dataset results with images of varied field of view. In: Misura/Dismisura| Measure/Out of Measure. Franco Angeli, pp. 471–482.
27.
LundbergSMLeeS-I (2017) A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems30: 07874.
28.
NardoneAChiangJCorburnJ (2020) Historic redlining and urban health today in US cities. Environmental Justice13(4): 109–119. https://doi.org/10.1089/env.2020.0011
NCRC (National Community Reinvestment Coalition) (2024) Decades of disinvestment: historic redlining and mortgage lending since 1981. Available at. https://ncrc.org/decades-of-disinvestment/
31.
OgawaYOkiTZhaoC, et al. (2024) Evaluating the subjective perceptions of streetscapes using street-view images. Landscape and Urban Planning247: 105073. https://doi.org/10.1016/j.landurbplan.2024.105073
32.
PowellRPorterJ (2023) Redlining, concentrated disadvantage, and crime: the effects of discriminatory government policies on urban violent crime. American Journal of Criminal Justice48(5): 1132–1156. https://doi.org/10.1007/s12103-022-09688-3
ShynuRSuseelanA (2023) Human cognition and emotional response towards visual environmental features in an urban built context: a systematic review on perception-based studies. Architectural Science Review66(6): 468–478. https://doi.org/10.1080/00038628.2023.2232339
35.
SunHZhangNJiangY, et al. (2026) A study on the coupling mechanism between the urban environment and depression perception based on deep learning and street view image. Scientific Reports16: 5856. https://doi.org/10.1038/s41598-026-36804-8
36.
SwopeCBHernándezDCushingLJ (2022) The relationship of historical redlining with present-day neighborhood environmental and health outcomes: a scoping review and conceptual model. Journal of Urban Health99(6): 959–983. https://doi.org/10.1007/s11524-022-00665-z
WangZItoKBiljeckiF (2024) Assessing the equity and evolution of urban visual perceptual quality with time series street view imagery. Cities145: 104704. https://doi.org/10.1016/j.cities.2023.104704
39.
XuXQiuWLiW, et al. (2022) Associations between street-view perceptions and housing prices: subjective vs. objective measures using computer vision and machine learning techniques. Remote Sensing14(4): 891. https://doi.org/10.3390/rs14040891
40.
YangYChoANguyenQ, et al. (2023) Association of neighborhood racial and ethnic composition and historical redlining with built environment indicators derived from street view images in the US. JAMA Network Open6(1): e2251201. https://doi.org/10.1001/jamanetworkopen.2022.51201
41.
YıldızSKıvrakSArslanG (2018) Built environment design-economic sustainability relationship in urban renewal. Journal of Construction Engineering, Management & Innovation1(1): 33–42. https://doi.org/10.31462/jcemi.2018.01033042
ZhaoHShiJQiX, et al. (2017) Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA, 21–26 July 2017, pp. 2881–2890.
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.
