Abstract
Limited by the noise, missing data and varying sampling density of the point clouds, planar primitives are prone to be lost during plane segmentation, leading to topology errors when reconstructing complex building models. In this paper, a pipeline to recover the broken topology of planar primitives (TopoLAP) is proposed to reconstruct level of details 3 (LoD3) models. Firstly, planar primitives are segmented from the incomplete point clouds and feature lines are detected both from point clouds and images. Secondly, the structural contours of each plane segment are reconstructed by subset selection from intersections of these feature lines. Subsequently, missing planes are recovered by plane deduction according to the relationships between linear and planar primitives. Finally, the manifold and watertight polyhedral building models are reconstructed based on the optimized PolyFit framework. Experimental results demonstrate that the proposed pipeline can handle partial incomplete point clouds and reconstruct the LoD3 models of complex buildings automatically. A comparative analysis indicates that the proposed method performs better to preserve sharp edges and achieves a higher fitness and correction rate than rooftop-based modeling and the original PolyFit algorithm.
Highlights
Three-dimensional building models, as the dominant type of man-made object in urban scenes, play an important role in the foundation of the smart city
The ISPRS test project on urban classification and 3D building reconstruction gives a comprehensive conclusion towards rooftop modeling from point clouds and/or images [6]
For the sake of clarity, linear primitives are divided into four categories according to their relative position attribute to candidate planes and other line segments: border line, crease line, inner edge, and needle line
Summary
Three-dimensional building models, as the dominant type of man-made object in urban scenes, play an important role in the foundation of the smart city. The ISPRS test project on urban classification and 3D building reconstruction gives a comprehensive conclusion towards rooftop modeling from point clouds and/or images [6]. Modeling without the façade points reduces the level of details and leaves the generalized boundaries of roofs inaccurate without the constraint of adjacent façades. Proliferation in the fields of laser scanning and imaging sensors enable the point clouds, either acquired fRreommote Sleings.h20t19d, 1e1t, ex cFOtiRoPnEEaRnRdEVIrEaWnging (LiDAR) or photogrammetry, to describe2loafr2g2 e-area 3D scenes efficiently, providing a good data foundation for building reconstruction with a higher level of detail. After a brief survey on related work given in An opSoeftcithtmieoinpzr2eo,dpaonpseoidvpemervleiitnehweodotoafroerueerxcapoplnapisrnoteraduchicntiSspeecxotpiloyrnehs4seeaddnrdianSleSmcetcitooinodn5e.3lT.shSeeuffibesxepcqieuerienmnttellynyt,swdaeritetahiclaehrdriiageldhgoofiruittthnamnedsss to point clouddsisacnusdsehdiginhSceoctriorenc6t.nFeisnsalolyf, pthleancoanrcplursiimonitiisvgeivs.en in Section 7 drawn from the experimental.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
