Abstract

Geometric-semantic coherent building models are demanding in many geoscience applications. Conventional building modeling methods often rely on successive roof plane segmentation and fitting. The subsequent reconstruction procedure is difficult to assure topologic consistency and geometric accuracy. This article starts with a library of predefined building models or primitives, including pyramid, gable, hip, etc. We propose an optimal model fitting approach that holistically determines all of its parameters from segmented point cloud data. The approach is formulated as an optimization problem that minimizes the point-to-mesh distance between the point cloud and the meshed primitive model. Necessary constraints in the form of inequality equations are introduced to assure correct and reliable solution. For complex roofs consisting of several predefined primitive models, a hierarchical procedure is presented to reconstruct the major roof model and its superstructures sequentially. The CityGML LoD2 model is created from the parameterized primitives. The quality and performance of this approach are evaluated with airborne lidar and photogrammetric point clouds. Based on the experiments with 910 buildings, the primitive fitting accuracy is 7.8 cm and the corner uncertainty is 0.36 m or 0.78 times the ground point spacing; the building boundary consistency is 89.6%. The study demonstrates a piecewise continuous polyhedral building model can be determined through a holistic parameter optimization process. The resultant building models intrinsically best fit to the input point cloud with topologic integrity. The approach not only qualitatively generates semantic building models but also exhibits the potential for building reconstruction over large areas.

Highlights

  • THREE dimensional (3D) building models with detailed roofs are essential for a large number of geospatial applications, such as 3D Geographic Information Systems (GIS), urban planning, environmental simulation, energy consumption assessment, heritage preservation [1], and change detection [2]

  • Such solution has the advantage of reconstructing polyhedral building models with complex shapes, it is lack of topological integrity and geometric rigor, and sensitive to the incompleteness of input data caused by tree clutter, multi path reflectance, object overlap, or occlusion [12]

  • This paper presents a hierarchical holistic primitive fitting framework to optimally reconstruct geometrically and topologically correct CityGML LoD2 building models from

Read more

Summary

INTRODUCTION

THREE dimensional (3D) building models with detailed roofs are essential for a large number of geospatial applications, such as 3D Geographic Information Systems (GIS), urban planning, environmental simulation, energy consumption assessment, heritage preservation [1], and change detection [2]. Data-driven building reconstruction is a prevailing approach in the past decades, which usually starts with a segmentation of the individual building points into planar roof patches, followed by intersecting them into polygonal meshes This type of approach is based on individual plane fitting by using such algorithms as random sample consensus (RANSAC) [7], clustering [8], region growing [9], [10], or cost function based method [11], which achieve locally fitting optimal.

RELATED WORKS
Roof Structure Recognition
Parametric Roof Reconstruction
CityGML Model Reconstruction
Building Primitives
Primitive Parametrization
Objective Function
Boundary Conditions
Hierarchical Fitting
CITYGML MODEL GENERATION
EXPERIMENTS AND EVALUATION
Test Datasets
Building Primitive Recognition
Primitive Fitting
Reconstructed Buildings
DISCUSSION
Bias of Symmetric Primitives
Computational Performance
Comparison with other methods
Findings
VIII. CONCLUSION
Full Text
Published version (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