GEO AI-POWERED URBAN FOOTPRINTS

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 17 | 02 | Page :
    By

    Karthikey Sinha,

  • Sanjeev Kumar,

  1. Student, Department of Geo-informatics, Netaji Subhas University of Technology, Delhi, India
  2. Assistant Professor, Department of Geo-informatics, Netaji Subhas University of Technology, Delhi, India

Abstract

In the contemporary era, building footprints are of paramount importance for accurate and current inventories in the development of infrastructure and geospatial analysis. Traditional methods, relying on manual digitization, were largely unsustainable as the urban regions were growing rapidly. Manual digitization was expensive and lacked geometric precision. This paper introduces an automated, end-to-end GEO AI-powered framework for high-end fidelity building footprint extraction from Google Satellite Data. Our approach for this study uses a YOLOv11 instance segmentation model, using a 1280 x 1280 tiling strategy and a 0.40 confidence threshold. This study focuses on fine-tuning the challenges by providing crucial data for urban planning (growth and roads), Disaster response (tracking fire and floods), and climate studies enabling better management and prediction. Thus helps to understand and manage our planet without physical contact. The predicted pixel-based segmentation masks are transformed into polygons via a geospatial vectorization pipeline implemented using GDAL. Thus, the pipeline generated is precisely georeferenced with real-world attributes (UTM Zone 43N Projected Coordinate System) incorporating the calculated area (A). Thus, high efficiency and accuracy are achieved in transforming raw satellite data into GIS ready vector inventories. This study provides an automated solution for urban mapping, delivering high-quality geometric data for smart city applications.

Keywords: Building Footprint Extraction, Deep Learning, Georeferencing, GIS, Remote Sensing, YOLOv11 Instance Segmentation and Smart Cities

How to cite this article:
Karthikey Sinha, Sanjeev Kumar. GEO AI-POWERED URBAN FOOTPRINTS. Journal of Remote Sensing & GIS. 2026; 17(02):-.
How to cite this URL:
Karthikey Sinha, Sanjeev Kumar. GEO AI-POWERED URBAN FOOTPRINTS. Journal of Remote Sensing & GIS. 2026; 17(02):-. Available from: https://journals.stmjournals.com/jorsg/article=2026/view=245596


References

  1. Neyns R, Canters F. Mapping of urban vegetation with high- resolution remote sensing: A review. Remote sensing. 2022 Feb 21;14(4):1031.
  2. Blaschke T, Hay GJ, Kelly M, Lang S, Hofmann P, Addink E, Feitosa RQ, Van der Meer F, Van der Werff H, Van Coillie F, Tiede D. Geographic object-based image analysis–towards a new paradigm. ISPRS journal of photogrammetry and remote sensing. 2014 Jan 1;87:180-91.
  3. Benediktsson JA, Palmason JA, Sveinsson JR. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing. 2005 Feb 22;43(3):480-91.
  4. Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. InInternational Conference on Medical image computing and computer-assisted intervention 2015 Oct 5 (pp. 234-241). Cham: Springer international publishing.
  5. He K, Gkioxari G, Dollár P, Girshick R. Mask r-cnn. InProceedings of the IEEE international conference on computer vision 2017 (pp. 2961-2969).
  6. Ahmed SB, Habib S, Naveed K, Shakeel A, Rauf M. Efficient Vision Based Fall Detection For Elderly Surveillance Using YOLOv11. In2025 6th International Conference on Innovative Computing (ICIC) 2025 Dec 10 (pp. 1-6). IEEE. Available: https://github.com/ultralytics/ultralytics
  7. Han X, Chang J, Wang KJ. You only look once: Unified, real- time object detection. Procedia Computer Science. 2021 Jan;183(1):61-72.
  8. Bradski G. The opencv library. Dr. Dobb’s Journal: Software Tools for the Professional Programmer. 2000;25(11):120-3.
  9. Warmerdam F. The geospatial data abstraction library. InOpen source approaches in spatial data handling 2008 Jul 30 (pp. 87- 104). Berlin, Heidelberg: Springer Berlin Heidelberg.
  10. Chaurasiya M, Kumar S, Bhatt K, Sharma S. The interplay of SDGs and climate action: A quantitative analysis of regional income influences on SDG 13 progress. Physics and Chemistry of the Earth, Parts A/B/C. 2025 Sep 1;139:103939.
  11. Delmelle E, Bearman N, Yao XA. Developing geospatial analytical methods to explore and communicate the spread of COVID19. Cartography and geographic information science. 2024 Mar 3;51(2):193-9.
  12. Chaurasiya M, Chandra S, Kumar S, Sharma S, Kumar A. Integrative deep learning framework for analysing population density shifts and flood inundation patterns–a case study of the Sundarbans. Journal of Hydroinformatics. 2025 Jul 1;27(7):1071-83.
  13. Hu Q, Zhen L, Mao Y, Zhou X, Zhou G. Automated building extraction using satellite remote sensing imagery. Automation in Construction. 2021 Mar 1;123:103509.
Ahead of Print Subscription Original Research
Volume 17
02
Received 24/04/2026
Accepted 04/05/2026
Published 01/06/2026
Publication Time 38 Days
12

Login


My IP

PlumX Metrics