Automatic Verification of Building Depiction Errors in National Digital Maps via Context- and Boundary-Aware Segmentation

Accurate building representation in national digital maps is essential for ensuring reliable geospatial analyses and supporting policy and administrative decision-making.However, the current quality inspection system in Korea relies on manual sampling-based verification, which inspects only about 30% of each map sheet and therefore risks overlooking errors in the remaining data.In particular, depiction errors in building polygons-such as inaccurate outlines or positional shifts-can significantly degrade the reliability of digital maps, especially when they are used as ground truth for training and validating Artificial Intelligence (AI) models.This study proposes an automated verification framework that combines the complementary strengths of two segmentation approaches: SegFormer, which provides robust contextual awareness for detecting building areas, and Segment Anything Model 2 (SAM 2), which offers precise boundary delineation through prompt-based segmentation.To this end, we designed a contextand boundary-aware segmentation pipeline: SegFormer first identifies candidate building regions from high-resolution true orthoimages, while SAM 2 refines the building outlines at the object level using bounding-box prompts and a probability map derived from both models.This integration resolves undersegmentation issues observed in standalone SegFormer outputs and enables precise extraction of individual building footprints.Experiments were conducted in Seoul using a 2022 true orthoimage (Ground Sample Distance [GSD], 0.12 m) and the 1:5,000 national digital map.The results demonstrated a substantial improvement in segmentation accuracy: the one-to-one matching ratio between building objects increased from 61.46% (SegFormer alone) to 97.56% with the proposed method, while boundary accuracy (Boundary Intersection over Union, BIoU) improved from 65.85% to 72.60%.In depiction error verification, the method achieved 100% recall in detecting erroneous building polygons, ensuring that no actual errors were omitted.Although the precision was relatively low (6.93%) due to false alarms caused by occlusions and resolution limitations, this conservative detection approach offers a practical advantage: only error candidates need to be manually reviewed, reducing the inspection workload by approximately 75% compared to full manual verification.The proposed method highlights the potential of AI-based automation for nationwide digital map quality management.By fusing contextual and boundary-aware segmentation, it not only improves the precision of building footprint extraction but also provides a reproducible framework for efficient and consistent verification of depiction errors.This work lays the foundation for applying advanced segmentation techniques to operational digital map inspection and supports the development of scalable quality control systems for national geospatial datasets.