Abstract. As urban digital transformation advances, accurately extracting three-dimensional building footprints in complex urban environments has become a key challenge in 3D scene applications. Traditional building footprint extraction methods primarily rely on geometric features or texture information, but in densely built or occluded urban environments, achieving ideal extraction results is often difficult. To address this issue, this paper proposes a 3D building footprint extraction method based on spatial constraints. The method designs spatial constraint rules based on three dimensions: height, direction, and distance, combining geometric features with spatial distribution patterns. By adaptively adjusting thresholds, the method effectively improves building footprint extraction in dense urban environments. Experimental results show that the proposed method achieves an IoU of 91.5% in commercial dense areas (a 21.3% improvement over traditional methods), reduces directional error to 3.2° (a 74% decrease), increases recall rate in occlusion scenes to 89.4%, and processes a single scene in only 218 seconds (a 32% reduction). Memory usage is also reduced by 26%. This research provides a high-precision, high-efficiency solution for urban digital modeling, especially suitable for large-scale applications in planning, design, and disaster emergency management.
Liu et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: