Knowledge Based 3d Building Model Recognition Using Convolutional Neural Networks From Lidar and Aerial Imageries

Alidoost, F.; Arefi, Hossein

doi:10.5194/isprs-archives-xli-b3-833-2016

Cited by 10 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Points can be clustered into planes based on similar attributes, such as: normal vectors, distance to a localized fitted plane or height similarities (Rottensteiner et al, 2014). Current data-driven methodologies and algorithms may be divided into four (4) general categories: (a) plane fitting based methods, (b) filtering and thresholding based methods, (c) segmentation based methods and (d) different supervised classification methods (Makantasis et al, 2015;Alidoost and Arefi, 2016). In the recent literature there are several approaches trying to apply plane fitting based methods on 3D point clouds, derived either from active sensors (e.g., LiDAR) or produced through photogrammetric procedures.…”

Section: Related Workmentioning

confidence: 99%

“…Reconstructing 3D surfaces is a well-studied problem, attracting the growing interest of the scientific community, for many years. Although there is an impressive amount of different approaches (Yu et al, 2014;Makantasis et al, 2015;Yu et al, 2016;Alidoost and Arefi, 2016;Köhn et al, 2016;McClunea et al, 2016), aiming the 3D reconstruction of the real world, there is still room for improvements. In the proposed methodology, screened Poisson surface reconstruction (Kazhdan and Hoppe, 2013) is utilized, for the reconstruction of buildings roof tops in densely urbanized areas.…”

Section: Partial Surface Reconstructionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic 3d Reconstruction of Buildings Roof Tops in Densely Urbanized Areas

Gkeli

Ioannidis

2018

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

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> 3D reconstruction of the urban environment constitutes a well-studied problem in the field of photogrammetry and computer vision, attracting the growing interest of the scientific community, for many years. Although the current state of the art present very impressive results, there is still room for improvements. The production of reliable and accurate 3D reconstructions is useful for a wide range of applications, such as urban planning, GIS, tax assessment, cadastre, insurance, 3D city modelling, etc. In this paper, a methodology for the automatic 3D reconstruction of buildings roof tops in densely urbanized areas, utilizing dense point clouds data, is proposed. It consists of three (3) main phases, each of which comprises a set of processing steps. In the first phase, the point cloud is simplified and smoothed. Outliers and non-roof elements are detected and removed utilizing shape, position and area criteria. In the second phase, the geometry buildings roof tops is optimized, by detecting and normalizing the edges. In the last phase, the reconstruction of the buildings roof tops is conducted. A progressive process, utilizing a plane fitting algorithm in combination with Screened Poisson Surface Reconstruction is performed. Buildings roof tops surfaces are produced and optimized. A software tool is developed and utilized for the implementation of the proposed methodology. The produced results are assessed and a comparison with another open-source software is conducted. The proposed methodology seems to be effective providing satisfactory results, as it can manage properly the really noisy point clouds of densely urbanized environments.</p>

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Partial Surface Reconstructionmentioning

confidence: 99%

Automatic 3d Reconstruction of Buildings Roof Tops in Densely Urbanized Areas

Gkeli

Ioannidis

2018

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

View full text Add to dashboard Cite

show abstract

“…In the data-driven approach, points are allocated to planar surfaces to construct 3D building models, whilst the roof is constructed using roof surfaces derived from segmentation algorithms. A third option, comprising a combination of the data-driven and model-based approaches, is used to exploit the strengths of each method (Alidoost and Arefi 2016). In this paper, a model-based approach is used to classify roof types, and a fusion of model and data-driven approaches are used to construct a 3D LOD2 model of buildings.…”

Section: Introductionmentioning

confidence: 99%

Towards open-source LOD2 modelling using convolutional neural networks

Muftah

Rowan

Butler

2021

Model. Earth Syst. Environ.

View full text Add to dashboard Cite

The aim of this paper is to classify and segment roofs using vertical aerial imagery to generate three-dimensional (3D) models. Such models can be used, for example, to evaluate the rainfall runoff from properties for rainwater harvesting and in assessing solar energy and roof insulation options. Aerial orthophotos and building footprints are used to extract individual roofs and bounding boxes, which are then fed into one neural network for classification and then another for segmentation. The approach initially implements transfer learning on a pre-trained VGG16 model. The first step achieves an accuracy of 95.39% as well as a F1 score of 95%. The classified images are segmented using a fully convolutional network semantic segmentation model. The mask of the segmented roof planes is used to extract the coordinates of the roof edges and the nexus points using the Harris corner detector algorithm. The coordinates of the corners are then used to plot a 3D Level of Detail 2 (LOD2) representation of the building and the roof height is determined by calculating the maximum and minimum height of a Digital Surface Model LiDAR point cloud and known building height data. Subsequently the wireframe plot can be used to compute the roof area. This model achieved an accuracy of 80.2%, 96.1%, 96.0%, 85.1% and 91.1% for flat, hip, gable, cross-hip and mansard roofs, respectively.

show abstract

“…In recent years, deep learning (DL) based on the artificial neural networks is implemented to extract buildings and recognize 3D building models from LiDAR data [31][32][33]. Currently, most of the DL approaches in the field of remote sensing and geospatial engineering are focused on object detection, classification, and semantic segmentation primarily using imagery.…”

Section: Introductionmentioning

confidence: 99%

Determination of Building Model Key Points Using Multidirectional Shaded Relief Images Generated from Airborne LiDAR Data

Lee

2019

Journal of Sensors

View full text Add to dashboard Cite

Light detection and ranging (LiDAR) data collected from airborne laser scanner system is one of the major sources to reconstruct Earth’s surface features. This paper presents a method for detecting model key points (MKPs) of the buildings using LiDAR point clouds. The proposed approach utilizes shaded relief images (SRIs) derived from the LiDAR data. The SRIs based on the concept of the shape from shading could provide unique information about individual surface patches of the building roofs. The main advantage of the proposed approach is to detect directly MKPs, which are primitives for 3D building modeling, without segmenting point clouds. Depending on the location of the light source, the SRIs are created differently. Therefore, integration of the multidirectional SRIs created from different locations of the light source could provide more reliable results. In addition, the vertical exaggeration (i.e., scaling Z-coordinates) is also beneficial because constituent surface patches of the roofs in the SRIs created with vertically exaggerated LiDAR data are more distinguishable. To determine the MKPs of the roofs, building data was separated from other objects using modified marker-controlled watershed algorithm in accordance with criteria to specify buildings such as area, height, and standard deviation. This process could remove the unnecessary objects such as trees, vegetation, and cars. The curvature scale space (CSS) corner detector was used to determine MKP since this method is robust to geometric changes such as rotation, translation, and scale. The proposed method was applied to simulated and real LiDAR datasets with various roof types. The experimental results show that the proposed method is effective in determining MKPs of various roof types with high level of detail (LoD).

show abstract

Knowledge Based 3d Building Model Recognition Using Convolutional Neural Networks From Lidar and Aerial Imageries

Cited by 10 publications

References 35 publications

Automatic 3d Reconstruction of Buildings Roof Tops in Densely Urbanized Areas

Automatic 3d Reconstruction of Buildings Roof Tops in Densely Urbanized Areas

Towards open-source LOD2 modelling using convolutional neural networks

Determination of Building Model Key Points Using Multidirectional Shaded Relief Images Generated from Airborne LiDAR Data

Contact Info

Product

Resources

About