Density-Based Method for Building Detection From Lidar Point Cloud

Mahphood, A.; Arefi, H.

doi:10.5194/isprs-annals-x-4-w1-2022-423-2023

Cited by 3 publications

(2 citation statements)

References 20 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The process of building modeling at various levels of detail, from LoD0 to LoD2, has been extensively investigated [8][9][10][11][12][13][14][15][16][17]. New approaches to modeling buildings are being proposed based on the density of point clouds [18], normal vectors on minimal subsets of neighboring LiDAR points to determine characteristic points in roof creases [15], shape descriptors, and cubes that divide the point cloud into roof surface segments [19]. However, even sophisticated techniques will not be able to handle some intrinsic modeling problems [20,21].…”

Section: Introductionmentioning

confidence: 99%

Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data

Kurdi

Lewandowicz²,

Gharineiat

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The development of autonomous navigation systems requires digital building models at the LoD3 level. Buildings with atypically shaped features, such as turrets, domes, and chimneys, should be selected as landmark objects in these systems. The aim of this study was to develop a method that automatically transforms segmented LiDAR (Light Detection And Ranging) point cloud to create such landmark building models. A detailed solution was developed for selected buildings that are solids of revolution. The algorithm relies on new methods for determining building axes and cross-sections. To handle the gaps in vertical cross-sections due to the absence of continuous measurement data, a new strategy for filling these gaps was proposed based on their automatic interpretation. In addition, potential points associated with building ornaments were used to improve the model. The results were presented in different stages of the modeling process in graphic models and in a matrix recording. Our work demonstrates that complicated buildings can be represented with a light and regular data structure. Further investigations are needed to estimate the constructed building model with vectorial models.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data

Kurdi

Lewandowicz²,

Gharineiat

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Several methods were developed for ALS point cloud segmentation for building identi cation, which are categorized in general into: density-based segmentation (Mahphood & Are 2023), region-growing segmentation (Xu et al, 2017), and adaptive segmentation (Poz & Ywata, 2020). The traditional methods for buildings identi cation which are based on manual interpretation or rule-based analysis have limited performance in accurate buildings identi cation using ALS point cloud due to various geometrical complexities associated with the building and its surrounding, speci cally in urban environment.…”

Section: Introductionmentioning

confidence: 99%

3D-SegNet: A deep learning framework for three-dimensional airborne laser scanning point cloud segmentation for building identification

Yadav,

Singh

2023

Preprint

View full text Add to dashboard Cite

The airborne laser scanning (ALS), a state-of-the-art 3D mapping technique is used for the fast and comprehensive three-dimensional (3D) data acquisition of urban environment. In this paper, a 3D-SegNet method is presented for identification of buildings using 3D ALS point cloud data. This method is mainly divided into two main steps: data preprocessing, and SegNet convolutional neural network: Urban building segmentation. In data preprocessing, the various LiDAR and geometric features are generated using point-wise 3D analysis in local spherical neighborhood. These features are processed and rasterized into feature images. Feature images along with buildings masks are used for the proposed 3D-SegNet model training and testing. The proposed 3D-SegNet model is straightforward to implement, where accurate segmentation of buildings are effectively dealt in several complex cases, such as buildings with varying dimensions, incomplete building geometry and data gaps; overlapped and connected objects with one of the objects as building, etc. The 3D-SegNet method performance for buildings segmentation was reported as average IOU, accuracy and F1-score of 76.19%, 91.19% and 77.45%, respectively employing the method on two datasets having different scene complexity. The proposed method is straightforward to implement and can be used as standard tool in urban planning strategies formation.

show abstract

Building and Vegetation Classification from Airborne Laser Scanning Point Cloud

Singh,

Yadav

2023

2023 IEEE 7th Conference on Information and Communication Technology (CICT)

View full text Add to dashboard Cite

Density-Based Method for Building Detection From Lidar Point Cloud

Cited by 3 publications

References 20 publications

Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data

Modeling Multi-Rotunda Buildings at LoD3 Level from LiDAR Data

3D-SegNet: A deep learning framework for three-dimensional airborne laser scanning point cloud segmentation for building identification

Building and Vegetation Classification from Airborne Laser Scanning Point Cloud

Contact Info

Product

Resources

About