Interpretation of Urban Surface Models Using 2D Building Information

doi:10.1006/cviu.1998.0720

Computer Vision and Image Understanding

Volume 72, Issue 2, November 1998, Pages 204-214

https://doi.org/10.1006/cviu.1998.0720 Get rights and content

Abstract

In 3D building reconstruction the interpretation process can be simplified if digital surface models (DSM), which can either be derived from stereo matching of aerial images or be directly measured by scanning laser systems, are used in addition to or instead of image data. Images contain much information, but the resulting complexity causes enormous problems for an automatic interpretation of this data type. Since the information of a DSM is restricted to surface geometry its interpretation is simplified by the absence of unnecessary details. Nevertheless, due to insufficient spatial resolution and quality of the DSM, especially for these applications, optimal results can only be achieved by the use of additional data sources. Within the approach presented in this paper the segmentation of planar surfaces from the DSM is supported by existing ground plans. This 2D building information is also used to derive hypotheses on the possible roof shapes in order to obtain a 3D boundary representation based on the segmented planes.

References (13)

K. Price, A. Huertas, Using perceptual grouping to detect objects in aerial scenes, Proc. ISPRS Congress Comm. III,...
U. Lohr
Pushbroom laserscanning—First operational results
Geo. Inform. Systems
(1996)
A. Carosio
Three-dimensional synthetic landscapes: Data acquisition, modelling and visualization
Photogrammetric Week'95
(1995)
P. Krystek, Fully automatic measurement of digital elevation models with MATCH-T, Proceedings of the 43th...
H. Maitre et al.
Using models to improve stereo reconstruction
IEEE Trans. Pattern Anal. Machine Intell
(1992)
J.-L. Lotti, G. Giraudon, Adaptive window algorithm for aerial image stereo, Proc. ISPRS Congress Comm. III, München,...

There are more references available in the full text version of this article.

Cited by (25)

Cycle graph analysis for 3D roof structure modelling: Concepts and performance
2014, ISPRS Journal of Photogrammetry and Remote Sensing
Citation Excerpt :
Different approaches to building reconstructions from ALS point clouds have been proposed (e.g. Brenner, 2005; Musialski et al., 2012). Of these approaches, the model-driven categories opt for pre-defined model libraries (e.g. Maas and Vosselman, 1999; Haala and Brenner, 1998). Among other changes are the recent presentations of a building reconstruction approach by Lafarge et al. (2010) adopting Bayesian decisions rules to optimise parametric blocks placed on 2D-supports, and an introduction of generative statistics by Huang et al. (2013) to a reconstruction scheme, where pre-defined primitives have been combined and merged into an entire roof.
The paper presents a cycle graph analysis approach to the automatic reconstruction of 3D roof models from airborne laser scanner data. The nature of convergences of topological relations of plane adjacencies, allowing for the reconstruction of roof corner geometries with preserved topology, can be derived from cycles in roof topology graphs. The topology between roof adjacencies is defined in terms of ridge-lines and step-edges. In the proposed method, the input point cloud is first segmented and roof topology is derived while extracting roof planes from identified non-terrain segments. Orientation and placement regularities are applied on weakly defined edges using a piecewise regularization approach prior to the reconstruction, which assists in preserving symmetries in building geometry. Roof corners are geometrically modelled using the shortest closed cycles and the outermost cycle derived from roof topology graph in which external target graphs are no longer required. Based on test results, we show that the proposed approach can handle complexities with nearly 90% of the detected roof faces reconstructed correctly. The approach allows complex height jumps and various types of building roofs to be firmly reconstructed without prior knowledge of primitive building types.
Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts
2013, ISPRS Journal of Photogrammetry and Remote Sensing
Citation Excerpt :
The data sources used along with images cover a wide range. Until now, LIDAR data (e.g., Haala and Brenner, 1998; Haala and Brenner, 1999; Hongjian and Shiqiang, 2006; Rottensteiner et al., 2007; Sohn and Dowman, 2007; Awrangjeb et al., 2010; Khoshelham et al., 2010; Hermosilla et al., 2011), SAR data (e.g., Tupin and Roux, 2003; Poulain et al., 2011; Wegner et al., 2011a), hyper-spectral data (McKeown et al., 1999), or existing building layers in 2-D GIS databases (e.g., Haala and Brenner, 1998; Haala and Brenner, 1999; Suveg and Vosselman, 2004; Bouziani et al., 2010; Vallet et al., 2011; Koc-San and Turker, 2012; Tack et al., 2012) have been successfully treated as supplementary sources to the image data. In addition, libraries of predefined building models (e.g., Fischer et al., 1998; Croitoru and Doytsher, 2003; Jaynes et al., 2003; Suveg and Vosselman, 2004) can also serve as additional data sources.
In this study, we propose a novel methodology for automated detection of buildings from single very-high-resolution (VHR) multispectral images. The methodology uses the principal evidence of buildings: the shadows that they cast. We model the directional spatial relationship between buildings and their shadows using a recently proposed probabilistic landscape approach. An effective shadow post-processing step is developed to focus on landscapes that belong to building regions. The building regions are detected using an original two-level graph theory approach. In the first level, each shadow region is addressed separately, and building regions are identified via iterative graph cuts designed in two-label partitioning. The final building regions are characterised in a second level in which the previously labelled building regions are subjected to a single-step multi-label graph optimisation performed over the entire image domain. Numerical assessments performed on 16 VHR GeoEye-1 images demonstrate that the proposed approach is highly robust and reliable. A distinctive specialty of the proposed approach is its applicability to buildings with diverse characteristics as well as to VHR images with significantly different illumination properties.
Automatic roof model reconstruction from ALS data and 2D ground plans based on side projection and the TMR algorithm
2011, ISPRS Journal of Photogrammetry and Remote Sensing
Citation Excerpt :
For a fully autonomous system, the integration of multiple data sources, such as multiple aerial images, ALS data, and 2D ground plans, might increase the reliability and degree of automation, but some constraints or limitations in certain aspects are unavoidable. Examples include the capability of handling a high density of built-up areas, occlusions from trees or neighboring buildings, bad image quality due to shadows, weather conditions or digitized imagery, insufficient image resolution or point clouds density, miscellaneous objects on the rooftop, etc. (Baillard and Zisserman, 2000; Brenner, 2000; Oude Elberink and Vosselman, 2009; Gruen et al., 2002; Haala and Brenner, 1998, 1999; Suveg and Vosselman, 2004). The purpose of feature extraction is to retrieve 3D primitives of building structure from images or laser scanning data, including corners, ridges, eaves, faces, and so on.
This paper presents an automatic roof model reconstruction method based on the side projection of airborne laser scanning (ALS) data. The proposed approach first detects the building’s primary orientation and decomposes multi-layer roofs into a single one. Then, 3D structural lines are detected and restored from the projected point clouds. Finally, a line-based roof model reconstruction algorithm, namely TIN-Merging and Reshaping (TMR), is proposed. The originality for 3D roof modeling is to perform geometric analysis and topology reconstruction from two 2D projections and then reshapes the roof using elevation information from the 3D structural lines or ALS data. Experimental results indicate a nearly 100% success rate for topology reconstruction can be achieved provided that the 3D structural lines can be enclosed as polygons. However, the success rate of the Reshaping stage is dependent on the complexity of the rooftop structure. With the exception of domed and multiple orientations roofs, which are not considered in the developed method, we achieve success rates around 92–95%. As for absolute accuracy, less that 50 cm of root-mean-square error is observed in all X–Y–Z directions. The results demonstrate that the proposed scheme is robust and accurate even when a group of connected buildings with multiple layers and mixed roof types is processed.
Automatic building extraction from DEMs using an object approach and application to the 3D-city modeling
2008, ISPRS Journal of Photogrammetry and Remote Sensing
In this paper, we present an automatic building extraction method from Digital Elevation Models based on an object approach. First, a rough approximation of the building footprints is realized by a method based on marked point processes: the building footprints are modeled by rectangle layouts. Then, these rectangular footprints are regularized by improving the connection between the neighboring rectangles and detecting the roof height discontinuities. The obtained building footprints are structured footprints: each element represents a specific part of an urban structure. Results are finally applied to a 3D-city modeling process.
Automatic object extraction from aerial imagery - a survey focusing on buildings
1999, Computer Vision and Image Understanding
This paper surveys the state-of-the-art automatic object extraction techniques from aerial imagery. It focuses on building extraction approaches, which present the majority of the work in this area. After proposing well-defined criteria for their assessment, characteristic approaches are selected and assessed, based on their models and strategies. The assessment gives rise to a combined model and strategy covering the current knowledge in the field. The model comprises: the derivation of characteristic properties from the function of objects; three-dimensional geometry and material properties; scales and levels of abstraction/aggregation; local and global context. The strategy consists of grouping, focusing on different scales, context-based control and generation of evidence from structures of parts, and fusion of data and algorithms. Many ideas which have not been explored in depth lead to promising directions for further research.
An Analysis of the Three-Dimensional Modelling Using LiDAR Data and Unmanned Aerial Vehicle (UAV) (Case Study: Institut Teknologi Sepuluh Nopember, Sukolilo Campus)
2023, IOP Conference Series: Earth and Environmental Science

View all citing articles on Scopus

^☆: D. FritschD. Hobbie

^f1: [email protected]

View full text

Regular ArticleInterpretation of Urban Surface Models Using 2D Building Information☆

Abstract

Pushbroom laserscanning—First operational results

Geo. Inform. Systems

Three-dimensional synthetic landscapes: Data acquisition, modelling and visualization

Photogrammetric Week'95

Using models to improve stereo reconstruction

IEEE Trans. Pattern Anal. Machine Intell

Regular Article
Interpretation of Urban Surface Models Using 2D Building Information☆