Deep Learning–Based Semantic Segmentation for Evaluating Urban Environmental Quality and Walkability in Dongdaemun
Article Sidebar
Main Article Content
Abstract
This study evaluates environmental quality and urban walkability in the Dongdaemun district through geospatial semantic segmentation of street-view imagery. A DeepLab ResNet101 model, pre-trained on the ADE20K dataset and implemented using the GluonCV framework, was applied to Google Street View images collected at 40-meter intervals in four cardinal directions. Pixel-level segmentation was used to quantify key environmental features such as greenery, sky visibility, pavement, and road surfaces. Based on these visual attributes, composite indicators representing comfort, convenience, and safety were derived, leading to the calculation of an Integrated Visual Walkability index. The results reveal clear spatial variations in walkability across the study area, highlighting areas with favorable pedestrian environments and zones requiring improvement. Although the analysis is constrained by image quality and spatial coverage, the findings demonstrate the effectiveness of deep learning–based semantic segmentation for large-scale environmental assessment. This approach provides a scalable and data-driven framework to support evidence-based urban planning and sustainable city development.
Downloads
Article Details
References
Alvarez, F., Garcia, P. (2025). Evaluating Walkability with Objective Street-View Measures and Machine Learning Regression Models. Transp. Res. Part D, 112,103556.
Brown, C., Green, S. (2025). Assessing Visual Crowdedness and Walkability Using Automated Street-Level Image Analysis. Urban Plan, 10(2),121–136.
Chen, L., Yu, H., Li, K. (2025). Deep Learning and Street-View Analytics to Measure Perceived Walkability in Dense Urban Areas. Buildings, 15(1),113.
Cheng, G., Han, J., Lu, X., Yang, C. (2022). Remote sensing image scene classification using deep learning: A review. Inf. Fusion, 86,102–119.
Choi, J., Kang, Y. (2025). Modeling and explaining perceived walkability in urban environments using street view images and explainable AI. Spat. Inf. Res, 33(6),1–16.doi:10.1007/s41324-025-00656-7.
Choi, J., Noh, S., Kim, S., Kang, Y. (2024). Assessing Walkability Using Street View Images and Semantic Segmentation Technique. J. th Korean Geogr. Soc, 2024, 673–687.
Dyck, D. Van, Cardon, G., Deforche, B., De Bourdeaudhuij, I. (2011). Do adults like living in high-walkable neighborhoods? Associations of walkability parameters with neighborhood satisfaction and possible mediators. Heal. Place, 17(4), 971–977.doi:10.1016/j.healthplace.2011.04.001.
Dyck, D. Van, Cardon, G., Deforche, B., Sallis, J.F., Owen, N., De Bourdeaudhuij, I. (2010). Neighborhood SES and walkability are related to physical activity behavior in Belgian adults. Prev. Med. (Baltim), 50(SUPPL.), 74–79.doi:10.1016/j.ypmed.2009.07.027.
Forum NH. (2007). Building health: creating and enhancing places for healthy, active lives: blueprint for action. Volume ke-1. London UK.
Ghose, H., Rai, A. (2025). Assessing the Pedestrian Infrastructure for Integrated Visual Walkability of Kolkata Municipal Corporation using Deep Learning based Geospatial Artificial Intelligence (Geo AI). ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci, X-5/W2-2025(September), 209–218.doi:10.5194/isprs-annals-X-5-W2-2025-209-2025.
Hamim, O.F., Kancharla, S.R., Ukkusuri, S.V. (2024). Mapping sidewalks on a neighborhood scale from street view images. Environ. Plan. B Urban Anal. City Sci, 51(4), 823–838.doi:10.1177/23998083231200445.
Handy, S.L., Boarnet, M.G., Ewing, R., Killingsworth, R.E. (2002). How the built environment affects physical activity: Views from urban planning. Am. J. Prev. Med, 23(2 SUPPL. 1), 64–73.doi:10.1016/S0749-3797(02)00475-0.
Huang, Z., Wang, B., Luo, S., Wang, M., Miao, J., Jia, Q. (2024). Integrating Streetscape Images, Machine Learning, and Space Syntax to Enhance Walkability: A Case Study of Seongbuk District, Seoul. Land, 13(10).doi:10.3390/land13101591.
Hwang, J., Nam, K., Lee, C. (2024). Spatial Image-Based Walkability Evaluation Using Regression Model. Appl. Sci, 14(10).doi:10.3390/app14104079.
Li, Y., Huang, Y., Mai, G., Zhang, F. (2025). Learning Street View Representations with Spatiotemporal Contrast.
Liu, L., Silva, E., Wu, C., Wang, H. (2020). Finding the optimal street view sampling strategy to evaluate streetscape features. Int. J. Geogr. Inf. Sci, 34(4), 801–823.
Michael, Y.L., Green, M.K., Farquhar, S.A. (2006). Neighborhood design and active aging. Heal. Place, 12(4),734–740.doi:10.1016/j.healthplace.2005.08.002.
Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., Terzopoulos, D. (2022). Image Segmentation Using Deep Learning: A Survey. IEEE Trans. Pattern Anal. Mach. Intell, 44(7), 3523–3542.doi:10.1109/TPAMI.2021.3059968.
Mushkani, R., Koseki, S. (2026). Street review: A participatory AI-based framework for assessing streetscape inclusivity. Cities. 170(October 2025), 106602.doi:10.1016/j.cities.2025.106602.
Nguyen, T., Lee, K., Hoang, M. (2025). Semantic Segmentation of Street View Imagery to Quantify Visual Indicators for Urban Walkability. Remote Sens, 17(4),902.
Owen, N., Cerin, E., Leslie, E., duToit, L., Coffee, N., Frank, L.D., Bauman, A.E., Hugo, G., Saelens, B.E., Sallis, J.F. (2007). Neighborhood Walkability and the Walking Behavior of Australian Adults. Am. J. Prev. Med, 33(5), 387–395.doi:10.1016/j.amepre.2007.07.025.
Perez, J., Fusco, G. (2025). Streetscape Analysis with Generative AI (SAGAI): Vision-language assessment and mapping of urban scenes. Geomatica, 77(2), 0–3.doi:10.1016/j.geomat.2025.100063.
Pradana, M.R., Dimyati, M., Gamal, A. (2025). Harmonizing street-view semantics and spatial predictors for dominant urban visual composition modelling. Comput. Urban Sci, 5(1).doi:10.1007/s43762-025-00210-z.
Saelens, B.E., Sallis, J.F., Frank, L.D. (2003). Environmental correlates of walking and cycling: Findings from the transportation, urban design, and planning literatures. Ann. Behav. Med, 25(2), 80–91.doi:10.1207/S15324796ABM2502_03.
Sallis, J.F., Saelens, B.E., Frank, L.D., Conway, T.L., Slymen, D.J., Cain, K.L., Chapman, J.E., Kerr, J. (2009). Neighborhood built environment and income: Examining multiple health outcomes. Soc. Sci. Med, 68(7), 1285–1293.doi:10.1016/j.socscimed.2009.01.017.
Smith, A., Johnson, B., Wang, L. (2025). Assessing Walkability with Deep CNNs by Integrating Objective and Subjective Urban Qualities. Sustain. Cities Soc. 133:106863.
Wilson, E., Taylor, J. (2025). AI-Based Sidewalk and Greenery Analysis for Pedestrian Safety and Comfort. Sustainability, 17(1),80.
Wilson, K., Elliott, S., Law, M., Eyles, J., Jerrett, M., Keller-Olaman, S. (2004). Linking perceptions of neighbourhood to health in Hamilton, Canada. J. Epidemiol. Community Health, 58(3),192–198.doi:10.1136/jech.2003.014308.
Yang, X., Li, T., Cao, Y., Zheng, X., Tang, L. (2025). A novel framework integrating GeoAI and human perceptions to estimate walkability in Wuhan, China. Sci. Rep, 15(1),1–12.doi:10.1038/s41598-025-09779-1.
Yu, C-Y. (2024). Deep Learning Techniques to Evaluate Changes in Walkability in Downtown Orlando via Street Panorama Imagery. Findings, 1–7.doi:10.32866/001c.123767.
Zhang, F., Zhou, B., Liu, L., Liu, Y., Fung, H., Lin, H., Ratti, C. (2019). Measuring human perceptions of the built environment using street view images: A review of advances, limitations, and opportunities. Comput. Environ. Urban Syst, 78, 101387.
Zhang, Y., Khan, M.A., Liu, L. (2025.) GeoAI-Based Semantic Segmentation for Assessing Walkability and Urban Greenery. ISPRS Int. J. Geo-Inf, 14(3),142.
Zhou, H., He, S., Cai, Y., Wang, M., Su, S. (2019). Social inequalities in neighborhood visual walkability: Using street view imagery and deep learning technologies to facilitate healthy city planning. Sustain. Cities Soc, 50, 101605.doi:10.1016/j.scs.2019.101605.