Big-Data Approach for Three-Dimensional Building Extraction from Aerial Laser Scanning

Aljumaily, Harith; Laefer, Debra F.; Cuadra, Dolores

doi:10.1061/(asce)cp.1943-5487.0000524

Cited by 27 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of these technologies, airborne laser scanning (ALS) has the highest accuracy in parameterizing building morphology, ranging from simple footprint identification [17] to complicated 3D structure and roof plane modeling [14,18]. State-of-the-art ALS approaches have also achieved very high accuracy in complex urban environments by integrating aerial imagery [19], city administrative data [20], architectural knowledge [21], and the Big Data approach [22].Despite these promising results, there have been relatively few published studies on such methods being applied to large areas [23]. Furthermore, ALS data sources and aerial images are often under the control of government ministries, and, due to high operational costs, they are not available in many parts of the world [24].…”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Digital Building Height Models Extracted from AW3D, TanDEM-X, ASTER, and SRTM Digital Surface Models over Yangon City

2018

View full text Add to dashboard Cite

Vertical urban growth in the form of urban volume or building height is increasingly being seen as a significant indicator and constituent of the urban environment. Although high-resolution digital surface models can provide valuable information, various places lack access to such resources. The objective of this study is to explore the feasibility of using open digital surface models (DSMs), such as the AW3D30, ASTER, and SRTM datasets, for extracting digital building height models (DBHs) and comparing their accuracy. A multidirectional processing and slope-dependent filtering approach for DBH extraction was used. Yangon was chosen as the study location since it represents a rapidly developing Asian city where urban changes can be observed during the acquisition period of the aforementioned open DSM datasets (2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011). The effect of resolution degradation on the accuracy of the coarse AW3D30 DBH with respect to the high-resolution AW3D5 DBH was also examined. It is concluded that AW3D30 is the most suitable open DSM for DBH generation and for observing buildings taller than 9 m. Furthermore, the AW3D30 DBH, ASTER DBH, and SRTM DBH are suitable for observing vertical changes in urban structures.2 of 25 SAR (synthetic aperture radar) pairs [16]. Of these technologies, airborne laser scanning (ALS) has the highest accuracy in parameterizing building morphology, ranging from simple footprint identification [17] to complicated 3D structure and roof plane modeling [14,18]. State-of-the-art ALS approaches have also achieved very high accuracy in complex urban environments by integrating aerial imagery [19], city administrative data [20], architectural knowledge [21], and the Big Data approach [22].Despite these promising results, there have been relatively few published studies on such methods being applied to large areas [23]. Furthermore, ALS data sources and aerial images are often under the control of government ministries, and, due to high operational costs, they are not available in many parts of the world [24]. Since several such regions are also undergoing rapid urban growth and will potentially face the associated adverse environmental impacts and safety concerns, it is necessary to monitor their urban volumes or building heights. At the same time, the quality and quantity of satellite images as well as the capabilities of sophisticated algorithms for DSM and DBH computations have increased dramatically in recent years [25]. Although such high-resolution satellite datasets are available for a fraction of the cost compared with ALS data, they are prohibitively expensive to obtain at the global scale. Despite various applications for building height data, there is still no such global dataset available that is comparable to the 'Global Rural-Urban Mapping Project (GRUMP) Urban Extents Grid, v1' [26,27] or the 'Global Urban Heat Island (UHI)' dataset [28]. Being able to derive building heights at a global scale is crucial not only for places that lack acce...

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Comparison of Digital Building Height Models Extracted from AW3D, TanDEM-X, ASTER, and SRTM Digital Surface Models over Yangon City

2018

View full text Add to dashboard Cite

show abstract

“…In recent years, studies on building extraction, reconstruction and change detection have made significant advances and a wide range of methods have been proposed on façade segmentation and opening area detection [2], building extraction [3][4][5], change detection and map database update [1,[6][7][8], roof plane extraction [9] and 3-D reconstruction [10]. A number of techniques [11,12] have also been proposed for evaluation of these methods.…”

Section: Related Workmentioning

confidence: 99%

An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection

2018

View full text Add to dashboard Cite

Three-dimensional (3-D) reconstruction of building roofs can be an essential prerequisite for 3-D building change detection, which is important for detection of informal buildings or extensions and for update of 3-D map database. However, automatic 3-D roof reconstruction from the remote sensing data is still in its development stage for a number of reasons. For instance, there are difficulties in determining the neighbourhood relationships among the planes on a complex building roof, locating the step edges from point cloud data often requires additional information or may impose constraints, and missing roof planes attract human interaction and often produces high reconstruction errors. This research introduces a new 3-D roof reconstruction technique that constructs an adjacency matrix to define the topological relationships among the roof planes. It identifies any missing planes through an analysis using the 3-D plane intersection lines between adjacent planes. Then, it generates new planes to fill gaps of missing planes. Finally, it obtains complete building models through insertion of approximate wall planes and building floor. The reported research in this paper then uses the generated building models to detect 3-D changes in buildings. Plane connections between neighbouring planes are first defined to establish relationships between neighbouring planes. Then, each building in the reference and test model sets is represented using a graph data structure. Finally, the height intensity images, and if required the graph representations, of the reference and test models are directly compared to find and categorise 3-D changes into five groups: new, unchanged, demolished, modified and partially-modified planes. Experimental results on two Australian datasets show high object-and pixel-based accuracy in terms of completeness, correctness, and quality for both 3-D roof reconstruction and change detection techniques. The proposed change detection technique is robust to various changes including addition of a new veranda to or removal of an existing veranda from a building and increase of the height of a building.

show abstract

“…Due to that fact, Aljumaily et al [58] found out that each building appears as a deep hole by viewing the bottom view of the DEM generated by ALS data. In addition, he extracted building using this character.…”

Section: Horizontal Hollow Ratio-based Building Point Identificationmentioning

confidence: 99%

Building Point Detection from Vehicle-Borne LiDAR Data Based on Voxel Group and Horizontal Hollow Analysis

et al. 2016

View full text Add to dashboard Cite

Information extraction and three-dimensional (3D) reconstruction of buildings using the vehicle-borne laser scanning (VLS) system is significant for many applications. Extracting LiDAR points, from VLS, belonging to various types of building in large-scale complex urban environments still retains some problems. In this paper, a new technical framework for automatic and efficient building point extraction is proposed, including three main steps: (1) voxel group-based shape recognition; (2) category-oriented merging; and (3) building point identification by horizontal hollow ratio analysis. This article proposes a concept of "voxel group" based on the voxelization of VLS points: each voxel group is composed of several voxels that belong to one single real-world object. Then the shapes of point clouds in each voxel group are recognized and this shape information is utilized to merge voxel group. This article puts forward a characteristic nature of vehicle-borne LiDAR building points, called "horizontal hollow ratio", for efficient extraction. Experiments are analyzed from two aspects: (1) building-based evaluation for overall experimental area; and (2) point-based evaluation for individual building using the completeness and correctness. The experimental results indicate that the proposed framework is effective for the extraction of LiDAR points belonging to various types of buildings in large-scale complex urban environments.

show abstract

Big-Data Approach for Three-Dimensional Building Extraction from Aerial Laser Scanning

Cited by 27 publications

References 25 publications

Comparison of Digital Building Height Models Extracted from AW3D, TanDEM-X, ASTER, and SRTM Digital Surface Models over Yangon City

Comparison of Digital Building Height Models Extracted from AW3D, TanDEM-X, ASTER, and SRTM Digital Surface Models over Yangon City

An Effective Data-Driven Method for 3-D Building Roof Reconstruction and Robust Change Detection

Building Point Detection from Vehicle-Borne LiDAR Data Based on Voxel Group and Horizontal Hollow Analysis

Contact Info

Product

Resources

About