Global Solutions to Building Segmentation and Reconstruction

Shan, Jie; Yan, Jixing; Jiang, Wanshou

doi:10.1201/9781315154381-15

Cited by 4 publications

(12 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In literature, several methods are suggested for constructing the reference model. In this context, Shan et al (2018) derive the reference model by manual segmentation of the building point cloud. Rottensteiner and Clode (2018) generate the reference model in a semiautomatic working environment by using digital aerial images and Lidar data.…”

Section: Feature-based Accuracymentioning

confidence: 99%

“…In urban areas, the extraction of building class from the city scene can be achieved automatically or manually before starting the modelling stage. In the context of automatic building modelling, two major approaches are presented in the literature, the model driven or parametric approach, and the data driven or non-parametric approach (Shan et al 2018 andTarsha Kurdi et al 2007).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of LiDAR Building Point Cloud with Reference Model for Deep Comprehension of Cloud Structure

Kurdi

Awrangjeb

2020

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

This paper studies the fidelity level of the extracted Lidar (LIght Detection And Ranging) building point cloud in relation to the original building.In this context, the building point cloud is compared with a reference model. This comparison allows a deep understanding of the point cloud structure with respect to both the actual building and the constructed model. Consequently, the source of the incompatibility in a (reference or constructed) building model is determined and described. Thus, this study considers four aspects of the building point cloud.First, the errors of building point cloud extraction and the undesirable points are quantified. Hence, it is found that the percentages of undesirable points are sometimes considerable (between 15% and 70%). Second, the evaluation of the fit of the altimetry with the reference model shows that the roof plane equations calculated from Lidar data can be more precise than those of reference model, Third, it is noted that the segmentability level between different point densities and building typologies are variable. Finally, the per plane comparison mentions the incompatibility of the plane boundaries of point cloud with reference model. Moreover, considerable differences are noted between the theoretical and the true point densities.

show abstract

Section: Feature-based Accuracymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Comparison of LiDAR Building Point Cloud with Reference Model for Deep Comprehension of Cloud Structure

Kurdi

Awrangjeb

2020

Canadian Journal of Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In order to test the accuracy of the filtering algorithm, four datasets are used (see Section 3). The roof point clouds of the selected buildings in the four datasets are manually extracted (point per point), since manual extraction is supposed to be more accurate than automatic (Shan, Yan, & Jiang, 2018), and then considered as references. In this context, it is beneficial to estimate the error of filtering.…”

Section: Filtering Of Building Point Cloudmentioning

confidence: 99%

“…In this context, it is beneficial to estimate the error of filtering. For this purpose, the confusion matrix is employed for calculating the correctness and the completeness accuracy indices (Shan et al, 2018). In this context, three elements from the confusion matrix will be employed: TP (true positive)—the common points of both reference and detected roof. FN (false negative)—the points of the reference not found in the detected roof. FP (false positive)—the points of the detected roof not found in the reference. …”

Section: Filtering Of Building Point Cloudmentioning

confidence: 99%

“…These indices count the number of roof planes that have an overlap of at least 50% with reference roof planes. For calculating these indices, the confusion matrix is employed (Shan et al, 2018). In this context, three elements from the confusion matrix are employed: TP, FN, and FP [see Section 4.5 and Equations (7)–(9) of Rutzinger, Rottensteiner, and Pfeifer (2009)].…”

Section: Automatic Calculation Of 2d Building Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic filtering and 2D modeling of airborne laser scanning building point cloud

Kurdi

Awrangjeb

Munir

2020

Transactions in GIS

View full text Add to dashboard Cite

This article suggests a new approach to automatic building footprint modeling using exclusively airborne LiDAR data. The first part of the suggested approach is the filtering of the building point cloud using the bias of the Z‐coordinate histogram. This operation aims to detect the points of roof class from the building point cloud. Hence, eight rules for histogram interpretation are suggested. The second part of the suggested approach is the roof modeling algorithm. It starts by detecting the roof planes and calculating their adjacency matrix. Hence, the roof plane boundaries are classified into four categories: (1) outer boundary; (2) inner plane boundaries; (3) roof detail boundaries; and (4) boundaries related to the missing planes. Finally, the junction relationships of roof plane boundaries are analyzed for detecting the roof vertices. With regard to the resulting accuracy quantification, the average values of the correctness and the completeness indices are employed in both approaches. In the filtering algorithm, their values are respectively equal to 97.5 and 98.6%, whereas they are equal to 94.0 and 94.0% in the modeling approach. These results reflect the high efficacy of the suggested approach.

show abstract

A new approach for roof segmentation from airborne LiDAR point clouds

Zhao

Guo

et al. 2021

Remote Sensing Letters

View full text Add to dashboard Cite

Global Solutions to Building Segmentation and Reconstruction

Cited by 4 publications

References 1 publication

Comparison of LiDAR Building Point Cloud with Reference Model for Deep Comprehension of Cloud Structure

Comparison of LiDAR Building Point Cloud with Reference Model for Deep Comprehension of Cloud Structure

Automatic filtering and 2D modeling of airborne laser scanning building point cloud

A new approach for roof segmentation from airborne LiDAR point clouds

Contact Info

Product

Resources

About