A Multi-Level 3D Building Reconstruction Framework Integrating LiDAR Point Cloud and Imagery-Based Building Footprints
LiDAR点群と画像ベース建物フットプリントを統合したマルチレベル3D建物再構築フレームワーク (AI 翻訳)
L. Lakshmanan, S. Nagarajan
🤖 gxceed AI 要約
日本語
本研究は、航空LiDAR点群とNAIP画像から抽出した建物フットプリントを統合し、マルチレベル3D建物モデルを半自動で再構築するワークフローを提案する。Mask R-CNNによるフットプリント抽出は、LiDAR参照データに対して平均IoU 0.8226を達成し、LOD2モデルでは境界認識メッシュ改良により屋根の連続性を向上させた。都市計画や防災、持続可能なインフラ開発への応用が期待される。
English
This study proposes a semi-automated workflow for multi-level 3D building reconstruction by integrating airborne LiDAR point clouds with building footprints extracted from NAIP imagery using Mask R-CNN. The footprint extraction achieved a mean IoU of 0.8226 against LiDAR-derived references, and LOD2 models were improved with boundary-aware mesh refinement. The method supports urban planning, disaster resilience, and sustainable infrastructure development.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本の都市計画や防災分野では、3D建物モデルはインフラ管理や災害対策に有用だが、GX政策との直接的な関連は薄い。ただし、持続可能な都市開発の基盤技術として、今後のGX関連施策への応用可能性はある。
In the global GX context
Globally, 3D building models are increasingly used for urban sustainability assessments, such as energy demand modeling and climate resilience planning. This workflow offers a scalable method for generating such models, which could support climate adaptation and sustainable infrastructure initiatives.
👥 読者別の含意
🔬研究者:3D建物再構築の効率的な手法として、都市の気候変動適応研究に応用可能。
🏢実務担当者:都市計画やインフラ管理の実務で、持続可能な開発のための3Dモデル生成に活用できる。
🏛政策担当者:都市の気候レジリエンス向上のための基盤データ整備に寄与する可能性がある。
📄 Abstract（原文）
Three-dimensional (3D) building reconstruction plays an important role in urban planning, disaster resilience, and sustainable infrastructure development. Conventional approaches based on airborne Light Detection and Ranging (LiDAR) data can be computationally intensive and often require large labeled datasets, particularly for large-scale applications. This study presents a semi-automated workflow for reconstructing multi-level 3D building models by integrating airborne LiDAR point cloud data with building footprints extracted from National Agriculture Imagery Program (NAIP) imagery using a Mask Region-Based Convolutional Neural Network (Mask R-CNN). The extracted footprints were used to spatially isolate building-specific LiDAR subsets for 3D reconstruction. The proposed methodology generated building models at multiple Levels of Detail (LOD), ranging from two-dimensional (2D) footprints to volumetric representations with detailed roof structures. Building footprint extraction was quantitatively evaluated against LiDAR-derived footprints generated using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), which served as the reference dataset and detected buildings obscured by tree canopy. The reconstruction workflow was implemented in Open3D and incorporated a boundary-aware mesh refinement strategy based on ear-clipping triangulation to improve rooftop continuity in LOD2 models. The proposed footprint extraction framework achieved a mean Intersection over Union (IoU) of 0.8226 relative to LiDAR-derived reference building footprints, indicating reliable building delineation that supports the proposed multi-level 3D building reconstruction workflow.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/urbansci10080442first seen 2026-08-09 05:52:37
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。