Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100789035> ?p ?o ?g. }
- W3100789035 endingPage "695" @default.
- W3100789035 startingPage "689" @default.
- W3100789035 abstract "Abstract. Building models are conventionally reconstructed by building roof points via planar segmentation and then using a topology graph to group the planes together. Roof edges and vertices are then mathematically represented by intersecting segmented planes. Technically, such solution is based on sequential local fitting, i.e., the entire data of one building are not simultaneously participating in determining the building model. As a consequence, the solution is lack of topological integrity and geometric rigor. Fundamentally different from this traditional approach, we propose a holistic parametric reconstruction method which means taking into consideration the entire point clouds of one building simultaneously. In our work, building models are reconstructed from predefined parametric (roof) primitives. We first use a well-designed deep neural network to segment and identify primitives in the given building point clouds. A holistic optimization strategy is then introduced to simultaneously determine the parameters of a segmented primitive. In the last step, the optimal parameters are used to generate a watertight building model in CityGML format. The airborne LiDAR dataset RoofN3D with predefined roof types is used for our test. It is shown that PointNet++ applied to the entire dataset can achieve an accuracy of 83% for primitive classification. For a subset of 910 buildings in RoofN3D, the holistic approach is then used to determine the parameters of primitives and reconstruct the buildings. The achieved overall quality of reconstruction is 0.08 meters for point-surface-distance or 0.7 times RMSE of the input LiDAR points. This study demonstrates the efficiency and capability of the proposed approach and its potential to handle large scale urban point clouds." @default.
- W3100789035 created "2020-11-23" @default.
- W3100789035 creator A5014509373 @default.
- W3100789035 creator A5043731325 @default.
- W3100789035 creator A5049801163 @default.
- W3100789035 date "2020-08-12" @default.
- W3100789035 modified "2023-10-12" @default.
- W3100789035 title "HOLISTIC PARAMETRIC RECONSTRUCTION OF BUILDING MODELS FROM POINT CLOUDS" @default.
- W3100789035 cites W1996749420 @default.
- W3100789035 cites W2000018820 @default.
- W3100789035 cites W2005126631 @default.
- W3100789035 cites W2156406284 @default.
- W3100789035 cites W2339077268 @default.
- W3100789035 cites W2560609797 @default.
- W3100789035 cites W2590920743 @default.
- W3100789035 cites W2594198114 @default.
- W3100789035 cites W2602540228 @default.
- W3100789035 cites W2603235839 @default.
- W3100789035 cites W2610213140 @default.
- W3100789035 cites W2761311588 @default.
- W3100789035 cites W2769284350 @default.
- W3100789035 cites W2802591237 @default.
- W3100789035 cites W2901893665 @default.
- W3100789035 cites W2910365069 @default.
- W3100789035 cites W2939384298 @default.
- W3100789035 cites W2955991110 @default.
- W3100789035 cites W2958712078 @default.
- W3100789035 cites W2963121255 @default.
- W3100789035 cites W2963727135 @default.
- W3100789035 cites W2981440248 @default.
- W3100789035 cites W3103830808 @default.
- W3100789035 doi "https://doi.org/10.5194/isprs-archives-xliii-b2-2020-689-2020" @default.
- W3100789035 hasPublicationYear "2020" @default.
- W3100789035 type Work @default.
- W3100789035 sameAs 3100789035 @default.
- W3100789035 citedByCount "3" @default.
- W3100789035 countsByYear W31007890352021 @default.
- W3100789035 countsByYear W31007890352022 @default.
- W3100789035 crossrefType "journal-article" @default.
- W3100789035 hasAuthorship W3100789035A5014509373 @default.
- W3100789035 hasAuthorship W3100789035A5043731325 @default.
- W3100789035 hasAuthorship W3100789035A5049801163 @default.
- W3100789035 hasBestOaLocation W31007890351 @default.
- W3100789035 hasConcept C105795698 @default.
- W3100789035 hasConcept C11413529 @default.
- W3100789035 hasConcept C117251300 @default.
- W3100789035 hasConcept C124101348 @default.
- W3100789035 hasConcept C124504099 @default.
- W3100789035 hasConcept C127413603 @default.
- W3100789035 hasConcept C131979681 @default.
- W3100789035 hasConcept C154945302 @default.
- W3100789035 hasConcept C181095308 @default.
- W3100789035 hasConcept C205649164 @default.
- W3100789035 hasConcept C2187777 @default.
- W3100789035 hasConcept C2524010 @default.
- W3100789035 hasConcept C2776748203 @default.
- W3100789035 hasConcept C2778530916 @default.
- W3100789035 hasConcept C28719098 @default.
- W3100789035 hasConcept C33923547 @default.
- W3100789035 hasConcept C41008148 @default.
- W3100789035 hasConcept C44154836 @default.
- W3100789035 hasConcept C5134670 @default.
- W3100789035 hasConcept C51399673 @default.
- W3100789035 hasConcept C62649853 @default.
- W3100789035 hasConcept C66938386 @default.
- W3100789035 hasConcept C89600930 @default.
- W3100789035 hasConcept C99636146 @default.
- W3100789035 hasConceptScore W3100789035C105795698 @default.
- W3100789035 hasConceptScore W3100789035C11413529 @default.
- W3100789035 hasConceptScore W3100789035C117251300 @default.
- W3100789035 hasConceptScore W3100789035C124101348 @default.
- W3100789035 hasConceptScore W3100789035C124504099 @default.
- W3100789035 hasConceptScore W3100789035C127413603 @default.
- W3100789035 hasConceptScore W3100789035C131979681 @default.
- W3100789035 hasConceptScore W3100789035C154945302 @default.
- W3100789035 hasConceptScore W3100789035C181095308 @default.
- W3100789035 hasConceptScore W3100789035C205649164 @default.
- W3100789035 hasConceptScore W3100789035C2187777 @default.
- W3100789035 hasConceptScore W3100789035C2524010 @default.
- W3100789035 hasConceptScore W3100789035C2776748203 @default.
- W3100789035 hasConceptScore W3100789035C2778530916 @default.
- W3100789035 hasConceptScore W3100789035C28719098 @default.
- W3100789035 hasConceptScore W3100789035C33923547 @default.
- W3100789035 hasConceptScore W3100789035C41008148 @default.
- W3100789035 hasConceptScore W3100789035C44154836 @default.
- W3100789035 hasConceptScore W3100789035C5134670 @default.
- W3100789035 hasConceptScore W3100789035C51399673 @default.
- W3100789035 hasConceptScore W3100789035C62649853 @default.
- W3100789035 hasConceptScore W3100789035C66938386 @default.
- W3100789035 hasConceptScore W3100789035C89600930 @default.
- W3100789035 hasConceptScore W3100789035C99636146 @default.
- W3100789035 hasLocation W31007890351 @default.
- W3100789035 hasLocation W31007890352 @default.
- W3100789035 hasOpenAccess W3100789035 @default.
- W3100789035 hasPrimaryLocation W31007890351 @default.
- W3100789035 hasRelatedWork W2100393170 @default.
- W3100789035 hasRelatedWork W2144311066 @default.
- W3100789035 hasRelatedWork W2363570766 @default.