Journal of Transport and Land Use

Scaling pedestrian crossing analysis to 100 U.S. cities via AI-based segmentation of satellite imagery

Marcel E. Moran

San José State University

https://orcid.org/0000-0002-5637-4971

Arunav Gupta

New York University

https://orcid.org/0000-0001-9073-1349

Jiali Qian

New York University

Debra Laefer

New York University

https://orcid.org/0000-0001-5134-5322

DOI: https://doi.org/10.5198/jtlu.2026.2771

Keywords: satellite imagery, active transportation, computer vision, pedestrian

---

Abstract

Accurately measuring street dimensions is essential to evaluating how their design influences both travel behavior and safety. However, gathering street-level information at city-scale with precision is difficult given the quantity and complexity of urban intersections. To address this challenge in the context of pedestrian crossings — a crucial component of walkability — we introduce a scalable and accurate method for automatically measuring crossing distance at both marked and unmarked crosswalks, applied to America’s 100 largest cities. First, OpenStreetMap coordinates were used to retrieve satellite imagery of intersections throughout each city — totaling roughly three million images. Next, Meta’s Segment Anything Model was trained on a manually labelled subset of these images to differentiate drivable from non-drivable surfaces (i.e., roads vs. sidewalks). Third, all available crossing edges from OpenStreetMap were extracted. Finally, crossing edges were overlaid on the segmented intersection images, and a grow-cut algorithm was applied to connect each edge to its adjacent non-drivable surface (e.g., sidewalk, private property, etc.), thus enabling the calculation of crossing distance. This achieved 93% accuracy in measuring crossing distance, with a median absolute error of 2 feet 3 inches (0.69 meters), when compared to manually verified data for an entire city. Across the 100 largest U.S. cities, median crossing distances ranged from 32 feet to 78 feet (9.8 – 23.8m), with detectable regional patterns. Median crossing distance also displayed a positive relationship with the cities’ year of incorporation, illustrating in a novel way how American city planning increasingly emphasizes wider (and more car-centric) streets. These findings identified opportunities to improve pedestrian safety and increase walkability at multiple scales, from the individual block to the entire city.

---

References

Abley, S., Turner, S. & Singh, R. (2011). Predicting walkability. IPENZ Transportation Group Conference, Auckland, NZ. https://www.researchgate.net/profile/Shane-Turner-5/publication/335339674_Predicting_Walkability/links/5d5fb5a6299bf1f70b05e08d/Predicting-Walkability.pdf

Agbangba, C. E., Aide, E. S., Honfo, H., & Glèlè Kakai, R. (2024). On the use of post-hoc tests in environmental and biological sciences: A critical review. Heliyon, 10(3), e24131. https://doi.org/10.1016/j.heliyon.2024.e25131

Ahmetovic, D., Manduchi, R., Coughlan, J. M., & Mascetti, S. (2017). Mind your crossings: Mining GIS imagery for crosswalk localization. ACM Transactions on Accessible Computing, 9(4), 1–25. https://doi.org/10.1145/3046790

Albert, A., Kaur, J., & Gonzalez, M. C. (2017). Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1357–1366. https://doi.org/10.1145/3097983.3098070

Bagwari, N., Kumar, S., & Verma, V. S. (2023). A comprehensive review on segmentation techniques for satellite images. Archives of Computational Methods in Engineering, 30(7), 4325–4358. https://doi.org/10.1007/s11831-023-09939-4

Bailey, L., & Vega-Barachowitz, D. (2012). Urban street design guide. NACTO. https://www.nyc.gov/html/dot/downloads/pdf/2012-nacto-urban-street-design-guide.pdf

Barrington-Leigh, C., & Millard-Ball, A. (2015). A century of sprawl in the United States. Proceedings of the National Academy of Sciences, 112(27), 8244–8249. https://doi.org/10.1073/pnas.1504033112

Barrington-Leigh, C., & Millard-Ball, A. (2020). Global trends toward urban street-network sprawl. Proceedings of the National Academy of Sciences, 117(4), 1941–1950. https://doi.org/10.1073/pnas.1905232116

Bennett, J. (2010). OpenStreetMap. Packt Publishing.

Björnberg, K. E., Hansson, S. O., Belin, M. Å., & Tingvall, C. (2022). The vision zero handbook: Theory, technology and management for a zero casualty policy. Springer Nature.

Boeing, G. (2017). OSMnx: New methods for acquiring, constructing, analyzing, and visualizing complex street networks. Computers, Environment and Urban Systems, 65, 126–139. https://doi.org/10.1016/j.compenvurbsys.2017.05.004

Boeing, G. (2021). Off the grid…and back again? The recent evolution of American street network planning and design. Journal of the American Planning Associa-tion, 87(1), 123–137. https://doi.org/10.1080/01944363.2020.1819382

Cova, E. (2024, April 3). Pedestrian fatalities at historic high. Smart Growth America. https://smartgrowthamerica.org/pedestrian-fatalities-at-historic-high/

Demetriou, D. (2016). Uncertainty of OpenStreetMap data for the road network in Cyprus. In Fourth International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2016), 9688, 43–52. https://doi.org/10.1117/12.2239612

Duncan, S., Chacra, A., Prakash, A., & Prati, F. (2016). Global street design guide. Global Designing Cities Initiative. https://globaldesigningcities.org/publication/global-street-design-guide/

Dwyer, B., Nelson, J., & Hansen, T. (2024). Roboflow (Version 1.0). Roboflow. https://roboflow.com

Feuer, W., Smith, P. Aun, E., Browne, P., Cao, J., Colasacco, E., Gudjonsson, S., Mezey, C., Micka-Maloy, K., & Pettinati, N. (2020). Street design manual (3rd ed.). New York City Department of Transportation.

Haverkamp, D. S. (2002). Extracting straight road structure in urban environments using IKONOS satellite imagery. Optical Engineering, 41(9), 2107–10. https://doi.org/10.1117/1.1496785

Islam, A., Mekker, M., & Singleton, P. A. (2022). Examining pedestrian crash frequency, severity, and safety in numbers using pedestrian exposure from Utah traffic signal data. Journal of Transportation Engineering, Part A: Systems, 148(10), 04022084. https://doi.org/10.1061/JTEPBS.0000737

Jiang, B. (2007). A topological pattern of urban street networks: Universality and peculiarity. Physica A: Statistical Mechanics and its Applications, 384(2), 647–655. https://doi.org/10.1016/j.physa.2007.05.064

Kadali, B. R., & Vedagiri, P. (2015). Evaluation of pedestrian crosswalk level of service (LOS) in perspective of type of land-use. Transportation Research Part A: Policy and Practice, 73, 113–124. https://doi.org/10.1016/j.tra.2015.01.009

Larsen, S.Ø., Koren, H., & Solberg, R. (2009). Traffic monitoring using very high resolution satellite imagery. Photogrammetric Engineering & Remote Sensing, 75(7), 859–869. https://doi.org/10.14358/PERS.75.7.859

Li, M., Sheng, H., Irvin, J., Chung, H., Ying, A., Sun, T., Ng, A.Y., & Rodriguez, D.A. (2023). Marked crosswalks in US transit-oriented station areas, 2007–2020: A computer vision approach using street view imagery. Environment and Planning B: Urban Analytics and City Science, 50(2), 350–369. https://doi.org/10.1177/23998083221112157

Ma, X., Zhang, X., Pun, M. O., & Huang, B. (2024). MANet: Fine-tuning segment anything model for multimodal remote sensing semantic segmentation. arXiv. https://doi.org/10.48550/arXiv.2410.11160

Martin, A. (2006). Factors influencing pedestrian safety: A literature review. PPR-241. TRL Limited. https://content.tfl.gov.uk/factors-influencing-pedestrian-safety-literature-review.pdf

McKight, P. E., & Najab, J. (2010). Kruskal-Wallis test. In The Corsini Encyclopedia of Psychology. John Wiley & Sons, Ltd. https://doi.org/10.1002/9780470479216.corpsy0491

Monsere, C., Figliozzi, M., Kothuri, S. M., Razmpa, A., & Hazel, D. (2016). Safety effectiveness of pedestrian crossing enhancements (SPR 778). Oregon Department of Transportation, FHWA, USDOT. https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1353&context=cengin_fac

Moran, M. E. (2020). What’s your angle? Analyzing angled parking to aid bike-network planning. Environment and Planning B: Urban Analytics and City Science, 48(7), 1912–1925. https://doi.org/10.1177/2399808320954205

Moran, M. E. (2022). Where the crosswalk ends: Mapping crosswalk coverage via satellite imagery in San Francisco. Environment and Planning B: Urban Analytics and City Science, 49(8), 2250–2266. https://doi.org/10.1177/23998083221081530

Moran, M. E., & Laefer, D. F. (2024). Multiscale analysis of pedestrian crossing distance. Journal of the American Planning Association, 1–15. https://doi.org/10.1080/01944363.2024.2394610

Osco, L. P., Wu, Q., de Lemos, E. L., Gonçalves, W. N., Ramos, A. P. M., Li, J., & Marcato, J. (2023). The segment anything model (SAM) for remote sensing applications: From zero to one shot. International Journal of Applied Earth Observation and Geoinformation, 124, 103540. https://doi.org/10.1016/j.jag.2023.103540

Ravi, N., Gabeur, V., Hu, Y. T., Hu, R., Ryali, C., Ma, T., Khedr, H., Rädle, R., Rol-land, C., Gustafson, L., Mintun, E., Pan, J., Vasedev Alwala, K., Carion, N., Wu, C., Girshick, R., Dollar, P., & Feichtenhofer, C. (2024). SAM 2: Segment anything in images and videos. Meta. https://ai.meta.com/research/publications/sam-2-segment-anything-in-images-and-videos/

Ren, S., Luzi, F., Lahrichi, S., Kassaw, K., Collins, L. M., Bradbury, K., & Malof, J. M. (2024). Segment anything, from space? Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 8355–8365. https://openaccess.thecvf.com/content/WACV2024/html/Ren_Segment_Anything_From_Space_WACV_2024_paper.html

Schneider, R. J. (2020). United States pedestrian fatality trends, 1977 to 2016. Transportation Research Record, 2674(9), 1069–1083. https://doi.org/10.1177/0361198120933636

Shannon, C. E. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27(3), 379–423. https://doi.org/doi:10.1002/j.1538-7305.1948.tb01338.x

Verma, R., & Ukkusuri, S. V. (2023). Crosswalk detection from satellite imagery for pedestrian network completion. Transportation Research Record, 2678(7), 845–856. https://doi.org/10.1177/03611981231210545

Vezhnevets, V., & Konouchine, V. (2005). Growcut: Interactive multi-label Nd image segmentation by cellular automata. In Proceedings of Graphicon, 1, 150–156. https://www.graphicon.ru/html/2005/proceedings/papers/VezhntvetsKonushin.pdf

Wilmut, K., & Purcell, C. (2022). Why are older adults more at risk as pedestrians? A systematic review. Human Factors, 64(8), 1269–1291. https://doi.org/10.1177/0018720821989511