Building Outline Extraction from Digital Elevation Models Using Marked Point Processes (original) (raw)
An automatic building extraction method: Application to 3D-city modeling
2006
Résumé: In this report, we present an automatic building extraction method from Digital Elevation Models (DEMs). The DEMs are generated using an algorithm based on a maximum-flow formulation using three-view images. First, the building footprints are extracted from the DEMs through an automatic method based on marked point processes: they are represented by an association of rectangles. Then, these rectangular building footprints are regularized by improving both the connection of the neighboring rectangles ...
ISPRS Journal of …, 2008
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.
Building extraction from digital elevation models
2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)., 2003
This paper describes an approach towards building extraction from Digital Elevation Models (DEMs). This approach is based on automatically generated DEMs with a resolution up to 0:5m and uses prior knowledge for the detection of buildings and their reconstruction.
Automated building extraction: comparison of paradigms and examples
This paper compares the paradigms of LiDAR and aerophotogrammetry in the context of building extraction and briefly discusses two roof building contour extraction methodologies. The assets and drawbacks of both data capturing system have been reported several times. In general, empirical and theoretical studies have confirmed that LiDAR methodologies are more suitable in deriving building heights and in extracting planar roof faces and ridges of the roof, whereas the aerophotogrammetry are more suitable in extracting building roof outlines. The first roof contour extraction methodology is based on a Digital Elevation Model (DEM), which is generated through the regularization of an available LiDAR point cloud. First, in order to detect aboveground objects, the DEM is segmented through a recursive splitting technique, followed by a Bayesian merging technique. The aboveground object polygons are extracted by using vectorization and polygonization techniques. Finally, the building roof contours are identified among all aboveground objects extracted previously, taking into account roof features and a Markov Random Field (MRF) model. The second methodology addresses the geometric refinement of laser-derived 3D roof contours by using high-resolution aerial images and a MRF model. First, 3D roof contours are projected onto the image-space. Then, the projected contours and the straight lines extracted from the image are used to establish an MRF description. The solution of the associate energy function provides groupings of straight lines representing roof building contours, which are topologically reconstructed based on the topology of the projected contours. Examples of applications are provided for both approaches.
AUTOMATIC BUILDING EXTRACTION FROM LIDAR DATA COVERING COMPLEX URBAN SCENES
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-3, 25-32, 2014
This paper presents a new method for segmentation of LIDAR point cloud data for automatic building extraction. Using the ground height from a DEM (Digital Elevation Model), the non-ground points (mainly buildings and trees) are separated from the ground points. Points on walls are removed from the set of non-ground points by applying the following two approaches: If a plane fitted at a point and its neighbourhood is perpendicular to a fictitious horizontal plane, then this point is designated as a wall point. When LIDAR points are projected on a dense grid, points within a narrow area close to an imaginary vertical line on the wall should fall into the same grid cell. If three or more points fall into the same cell, then the intermediate points are removed as wall points. The remaining non-ground points are then divided into clusters based on height and local neighbourhood. One or more clusters are initialised based on the maximum height of the points and then each cluster is extended by applying height and neighbourhood constraints. Planar roof segments are extracted from each cluster of points following a region-growing technique. Planes are initialised using coplanar points as seed points and then grown using plane compatibility tests. If the estimated height of a point is similar to its LIDAR generated height, or if its normal distance to a plane is within a predefined limit, then the point is added to the plane. Once all the planar segments are extracted, the common points between the neghbouring planes are assigned to the appropriate planes based on the plane intersection line, locality and the angle between the normal at a common point and the corresponding plane. A rule-based procedure is applied to remove tree planes which are small in size and randomly oriented. The neighbouring planes are then merged to obtain individual building boundaries, which are regularised based on long line segments. Experimental results on ISPRS benchmark data sets show that the proposed method offers higher building detection and roof plane extraction rates than many existing methods, especially in complex urban scenes.
Building Extraction from Laser Scanning Data
2008
Laser scanning systems are frequently used to provide the digital surface models, DSM, of the earth surface. Laser scanning is a fast and precise technique to extract information related with various objects (terrain and non-terrain). Automatic extraction of objects from laser scanner data and images has recently been an important subject. Buildings are the objects of the highest interest in 3D city modeling. Urban areas are rapidly changing due to human activities in construction, destruction or extension of topographic elements such as buildings and roads. This mandates the availability of fast data acquisition technique and automatic method for detecting and extracting 3D topographic objects from the data. In this paper, building details were extracted from laser scanning data. We used data which were produced by ISPRS III commission to be evaluated the filtering techniques belonging to Stuttgart city center. We produced an efficient algorithm with Hough transform technique by us...
Reports on Geodesy and Geoinformatics, 2017
Airborne laser scanning data (ALS) are used mainly for creation of precise digital elevation models. However, it appears that the informative potential stored in ALS data can be also used for updating spatial databases, including the Database of Topographic Objects (BDOT10k). Typically, geometric representations of buildings in the BDOT10k are equal to their entities in the Land and Property Register (EGiB). In this study ALS is considered as supporting data source. The thresholding method of original ALS data with the use of the alpha shape algorithm, proposed in this paper, allows for extraction of points that represent horizontal cross section of building walls, leading to creation of vector, geometric models of buildings that can be then used for updating the BDOT10k. This method gives also the possibility of an easy verification of up-to-dateness of both the BDOT10k and the district EGiB databases within geometric information about buildings. For verification of the proposed methodology there have been used the classified ALS data acquired with a density of 4 points/m 2. The accuracy assessment of the identified building outlines has been carried out by their comparison to the corresponding EGiB objects. The RMSE values for 78 buildings are from a few to tens of centimeters and the average value is about 0,5 m. At the same time for several objects there have been revealed huge geometric discrepancies. Further analyses have shown that these discrepancies could be resulted from incorrect representations of buildings in the EGiB database.
Accurate building outlines from als data
… Remote Sensing and …, 2004
Building detection from airborne laser scanner (ALS) data is a well-studied problem. Most existing building detection techniques rely on the generation of a digital terrain model (DTM) and a digital surface model (DSM) from last-pulse laser scanner data. The two are compared to form a normalised DSM (nDSM), from which the buildings are detected by use of a simple height threshold. Detection rates using a normalised DSM are very good, however, the accuracy of the building delineation is a function of ALS point spacing and system accuracy. To compete with the accuracies of photogrammetric and terrestrial measurement systems, the typical point spacing of 0.5m to 1.3m would need to be increased ten fold before the systems could be compared. Modern laser scanners can deliver either first-or last-pulse data collected in the same flight. If it exists, the difference between the first-pulse height and lastpulse height indicates that there is a height step somewhere in the laser spot. In a typical urban environment, these steps correspond to trees, power lines and building boundaries or edges. In this paper, first-and last-pulse laser scanner data is combined to improve the accuracy of the building outline delineation. Inclusion of the first-pulse data allows some ALS points to be identified as lying precisely on the building edge (outline) whilst interpolated edge points are used to supplement identified edge points. The identified edge points are assigned to building edges which are subsequently calculated from the points. The paper shows results from a real test site and examines the data acquisition process in order to maximise the benefit of using this method for building extent determination.
A new method for building extraction in urban areas from high-resolution LIDAR data
International Archives of Photogrammetry …, 2002
In this paper, a new method for the automated generation of 3D building models from directly observed point clouds generated by LIDAR sensors is presented. By a hierarchic application of robust interpolation using a skew error distribution function, the LIDAR points being on the terrain are separated from points on buildings and other object classes, and a digital terrain model (DTM) can be computed. Points on buildings have to be separated from other points classified as off-terrain points, which is accomplished by an analysis of the height differences of a digital surface model passing through the original LIDAR points and a digital terrain model. Thus, a building mask is derived, and polyhedral building models are created in these candidate regions in a bottom-up procedure by applying curvature-based segmentation techniques. Intermediate results will be presented for a test site located in the City of Vienna.
International Journal of Heritage in the Digital Era, 2014
This paper presents a semi-automatic approach for creating a 3D model from point clouds. The proposed approach consists in the development of two successive algorithms. First, the segmentation of the point cloud in geometric primitives is made based on RANSAC paradigm. Then, in a modelling step, the geometric primitives are used for either surface modelling or boundaries extraction and more particularly sectional view extraction. The whole approach is illustrated with examples of historical buildings. Regarding the results analysis, the developed approach is promising. Finally, potential improvements are suggested and should facilitate the creation of HBIM.