Model driven reconstruction of roofs from sparse LIDAR point clouds

Henn, André; Gröger, Gerhard; Stroh, Viktor; Plümer, Lutz

doi:10.1016/j.isprsjprs.2012.11.004

Cited by 118 publications

(95 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the promising ways to address this issue is to introduce some tags for storing the information of roofs and windows (e.g., shape, materials) and to define certain rules for transforming the semantics information to 3D geometries. Another possible way is to use footprints to detect and reconstruct the building structures (Dehbi et al, 2016;Henn et al, 2013). Furthermore, due to the limitation of the visualization tool we used, the building parts that are underground are not visualized.…”

Section: Discussionmentioning

confidence: 99%

Using Openstreetmap Data to Generate Building Models With Their Inner Structures for 3d Maps

Wang

Zipf

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:With the development of Web 2.0, more and more data related to indoor environments has been collected within the volunteered geographic information (VGI) framework, which creates a need for construction of indoor environments from VGI. In this study, we focus on generating 3D building models from OpenStreetMap (OSM) data, and provide an approach to support construction and visualization of indoor environments on 3D maps. In this paper, we present an algorithm which can extract building information from OSM data, and can construct building structures as well as inner building components (e.g., doors, rooms, and windows). A web application is built to support the processing and visualization of the building models on a 3D map. We test our approach with an indoor dataset collected from the field. The results show the feasibility of our approach and its potentials to provide support for a wide range of applications, such as indoor and outdoor navigation, urban planning, and incident management.

show abstract

Section: Discussionmentioning

confidence: 99%

Using Openstreetmap Data to Generate Building Models With Their Inner Structures for 3d Maps

Wang

Zipf

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Among these studies, model-driven methods assume a building is an assembly of roof primitives (e.g., gable roof and hipped roof), which and whose topology are predefined in a model library (Tarsha-Kurdi et al, 2007). To extract roof primitives from LiDAR point clouds, techniques such as invariant moments (Maas and Vosselman, 1999), graph matching (Oude Elberink and Vosselman, 2009;Verma et al, 2006;Xiong et al, 2014), Support Vector Machine (SVM) (Henn et al, 2013;Satari et al, 2012), RANdom SAmple Consensus (RANSAC) (Henn et al, 2013) and Reversible Jump Markov Chain Monte Carlo (RJMCMC) (Huang et al, 2013) are used. However, these approaches tend to fail when reconstructing complex roof shapes.…”

Section: Introductionmentioning

confidence: 99%

“…To alleviate this problem, complex roof shapes are usually decomposed into simple ones that are defined in the model library (Kada and McKinley, 2009). Among the reported studies, 2D-plans (Henn et al, 2013;Kada and McKinley, 2009), graph matching technique (Oude Elberink and Vosselman, 2009;Verma et al, 2006;Xiong et al, 2014) and convexity analysis (Lin et al, 2013) are used for this purpose. Unlike the aforementioned approaches, Huang et al (2013) extract roof primitives one by one from LiDAR points by using the RJMCMC technique.…”

Section: Introductionmentioning

confidence: 99%

A Global Solution to Topological Reconstruction of Building Roof Models From Airborne Lidar Point Clouds

Yan

Jiang

Shan

2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper presents a global solution to building roof topological reconstruction from LiDAR point clouds. Starting with segmented roof planes from building LiDAR points, a BSP (binary space partitioning) algorithm is used to partition the bounding box of the building into volumetric cells, whose geometric features and their topology are simultaneously determined. To resolve the inside/outside labelling problem of cells, a global energy function considering surface visibility and spatial regularization between adjacent cells is constructed and minimized via graph cuts. As a result, the cells are labelled as either inside or outside, where the planar surfaces between the inside and outside form the reconstructed building model. Two LiDAR data sets of Yangjiang (China) and Wuhan University (China) are used in the study. Experimental results show that the completeness of reconstructed roof planes is 87.5%. Comparing with existing data-driven approaches, the proposed approach is global. Roof faces and edges as well as their topology can be determined at one time via minimization of an energy function. Besides, this approach is robust to partial absence of roof planes and tends to reconstruct roof models with visibility-consistent surfaces.

show abstract

“…Methods for building detection or extraction from ALS data can be grouped into the following categories: building detection (Matikainen et al, 2003;Tóvari and Vögtle, 2004;TarshaKurdi et al, 2006), building roof contour extraction (Sampath and Shan, 2007;Wei, 2008;Perera et. al 2012), building roof extraction (Rottensteiner et al, 2005;Sampath and Shan, 2010), and building model extraction (Henn et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Extraction of Roof Lines From High-Resolution Images by a Grouping Method

Póz

Fernandes

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper proposes a method for extracting groups of straight lines that represent roof boundaries and roof ridgelines from highresolution aerial images using corresponding Airborne Laser Scanner (ALS) roof polyhedrons as initial approximations. The proposed method is based on two main steps. First, straight lines that are candidates to represent roof ridgelines and roof boundaries of a building are extracted from the aerial image. Second, a group of straight lines that represent roof boundaries and roof ridgelines of a selected building is obtained through the optimization of a Markov Random Field (MRF)-based energy function using the genetic algorithm optimization method. The formulation of this energy function considers several attributes, such as the proximity of the extracted straight lines to the corresponding projected ALS-derived roof polyhedron and the rectangularity (extracted straight lines that intersect at nearly 90 o ). Experimental results are presented and discussed in this paper.

show abstract

Model driven reconstruction of roofs from sparse LIDAR point clouds

Cited by 118 publications

References 27 publications

Using Openstreetmap Data to Generate Building Models With Their Inner Structures for 3d Maps

Using Openstreetmap Data to Generate Building Models With Their Inner Structures for 3d Maps

A Global Solution to Topological Reconstruction of Building Roof Models From Airborne Lidar Point Clouds

Extraction of Roof Lines From High-Resolution Images by a Grouping Method

Contact Info

Product

Resources

About