GeoAI-based post-segmentation quality validation of building footprints via spatial feature engineering
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a method to improve maps of building outlines made by computers from drone images, which often have mistakes. They used machine learning to automatically find and fix errors in these building shapes by looking at their geometry and context. Their approach works well even on new locations they hadn’t trained on, cutting errors by over 80%. This helps make building maps much cleaner and ready to use in geographic databases.
building footprint extractiondeep learningUAV imageryvectorizationmachine learning classifiersgeometric regularizationspatial-exclusivityDecision TreeGIS quality controlpost-segmentation
Authors
Shah Imran Ahsan Chowdhury, Kazi Jihadur Rashid, Rajsree Das Tuli, Rahul Saha, Bulbul Ahammad
Abstract
Deep learning-based building footprint extraction from high-resolution imagery often produces topologically inconsistent vectors unfit for direct GIS database ingestion. To address this, we present a multidomain GeoAI quality control framework that automates error detection to systematically purify vector footprint databases. Candidate footprints were generated across five UAV survey sites in Bangladesh using U-Net (ResNet-34) and SAM-LoRA (ViT-B). The extracted raster masks were vectorized, geometrically regularized, and consolidated under a spatial-exclusivity constraint to eliminate duplicate representations. We used twenty-four predictors capturing geometric, spatial-contextual, and raster-derived spectral and texture properties. Machine Learning (ML) classifiers were trained on a development partition (Sites B-D) and rigorously validated on a spatially independent test set (Site E) excluded from hyperparameter tuning and class balancing. The experimental results demonstrate that geometric and spatial-contextual predictors using Decision Tree (DT) provide the most effective discriminatory evidence for identifying object-level boundary deformations. DT achieved an accuracy of 95.31%, an F1-score of 91.06%, and a Matthews correlation coefficient (MCC) of 0.880 on the unseen testing site. At the database level, this framework successfully identified 87.34% of erroneous footprints while maintaining 98.31% of acceptable structures, reducing the residual error proportion from 27.32% to 4.62% and improving final database purity to 95.38%. This translates into a relative error reduction of 83.09%. The findings indicate that post-segmentation object-level ML provides a highly transferable, robust mechanism for automated quality assurance in production-ready geographic information system (GIS) workflows.