scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Automatic reconstruction of as-built building information models from laser-scanned point clouds: A review of related techniques

TL;DR: This article surveys techniques developed in civil engineering and computer science that can be utilized to automate the process of creating as-built BIMs and outlines the main methods used by these algorithms for representing knowledge about shape, identity, and relationships.
About: This article is published in Automation in Construction.The article was published on 2010-11-01. It has received 789 citations till now. The article focuses on the topics: Information model & Computer Aided Design.
Citations
More filters
Journal ArticleDOI
TL;DR: In this paper, the authors proposed an efficient method for constructing simplified polygonal faces from large-scale point-clouds by mapping point clouds onto 2D images and detecting bounded planar faces in the 2D image.
Abstract: The recent progress of mid-range and long-range laser scanners makes it possible to capture dense point-clouds of manufacturing plants. 3D models of manufacturing plants are useful for simulating the reorganizing of production lines. Since point-clouds are not structured and very large, it is often required to convert point-clouds into more concise models. So far, researchers have studied shape reconstruction of pipe structures by detecting cylindrical surfaces and estimating the lengths of the cylinders. On the other hand, few researches have discussed to extract polygonal faces from large-scale point-clouds. Planar faces may have very complicated boundaries, because point-clouds are noisy and often occluded by other surfaces in manufacturing plants. In this paper, we propose an efficient method for constructing simplified polygonal faces from large-scale point-clouds. In our method, we map each point-cloud onto a 2D image and detect bounded planar faces in the 2D image. Our method allows us to c...

20 citations


Additional excerpts

  • ...from large-scale point-clouds [1,2][4,5][7][13]....

    [...]

Journal ArticleDOI
TL;DR: The research investigates the definition of an HBIM targeted library, starting from surface surveying and representation towards the logic of object definition, in order to promote wider use and uptake of these 3D object modelling instruments.
Abstract: The paper illustrates the possibility to shift from a 3D content model to a Historic Building Information Modelling (HBIM) in order to support conservation and management of built heritage. This three-dimensional solution is based on parametric models, suitable for industrial elements and modern architecture, that can be usefully applied to heritage documentation and management of the data on conservation practices. In this sense, the research investigates the definition of an HBIM targeted library, starting from surface surveying and representation towards the logic of object definition. In order to promote wider use and uptake of these 3D object modelling instruments, some case studies are illustrated by the paper. Vault and wooden beam floor analysis show how HBIM for architectural heritage could be implemented in order to assemble different kind of data on historical buildings, such as e.g. dimensional, geometrical, thematic, historical and architectural information.

20 citations

Journal ArticleDOI
TL;DR: The fusion of spatial and visual data could significantly facilitate the current process of retrieving, modeling, and visualizing as-built information.
Abstract: As-built building information, including building geometry and features, is useful in multiple building assessment and management tasks. However, the current process for capturing, retrieving, and modeling such information is labor-intensive and time-consuming. In order to address these issues, this paper investigates the potentials of fusing visual and spatial data for automatically capturing, retrieving, and modeling as-built building geometry and features. An overall fusion-based framework has been proposed. Under the framework, pairs of 3D point clouds are progressively registered through the RGB-D (Red, Green, Blue plus Depth) mapping. Meanwhile, building elements are recognized based on their visual patterns. The recognition results can be used to label the 3D points, which could facilitate the modeling of building elements. So far, two pilot studies have been performed. The results show that a high degree of automation could be achieved for the registration of building scenes captured from different scans and the recognition of building elements with the proposed framework. The fusion of spatial and visual data could significantly facilitate the current process of retrieving, modeling, and visualizing as-built information.

20 citations


Additional excerpts

  • ...Meanwhile, the process for capturing, retrieving, and modeling such information has been identified as labor-intensive (Tang et al. 2010)....

    [...]

Journal ArticleDOI
TL;DR: In this article, a mixed pixel filter that minimizes the classification errors between valid points and mixed pixels is developed for improved dimension estimation using AMW laser scanners, where the distance measurement of mixed pixels was firstly formulated based on the working principle of laser scanners.
Abstract: Accurate dimension estimation is desired in many fields, but the traditional dimension estimation methods are time-consuming and labor-intensive. In the recent decades, 3D laser scanners have become popular for dimension estimation due to their high measurement speed and accuracy. Nonetheless, scan data obtained by amplitude-modulated continuous-wave (AMCW) laser scanners suffer from erroneous data called mixed pixels, which can influence the accuracy of dimension estimation. This study develops a mixed pixel filter for improved dimension estimation using AMCW laser scanners. The distance measurement of mixed pixels is firstly formulated based on the working principle of laser scanners. Then, a mixed pixel filter that can minimize the classification errors between valid points and mixed pixels is developed. Validation experiments were conducted to verify the formulation of the distance measurement of mixed pixels and to examine the performance of the proposed mixed pixel filter. Experimental results show that, for a specimen with dimensions of 840 mm × 300 mm, the overall errors of the dimensions estimated after applying the proposed filter are 1.9 mm and 1.0 mm for two different scanning resolutions, respectively. These errors are much smaller than the errors (4.8 mm and 3.5 mm) obtained by the scanner’s built-in filter.

20 citations


Cites background or methods from "Automatic reconstruction of as-buil..."

  • ...…applications of laser scanners have been reported, including reverse engineering (Chang and Chang, 2002; Son et al., 2002), 3Dmodel reconstruction (Tang et al., 2010; Bosche and Haas, 2008), construction progress tracking (Turkan et al., 2012; El-Omari and Moselhi, 2008), and dimension estimation…...

    [...]

  • ..., 2002), 3Dmodel reconstruction (Tang et al., 2010; Bosche and Haas, 2008), construction progress tracking (Turkan et al....

    [...]

Journal ArticleDOI
TL;DR: This work states that laser scanning technology is able to capture accurate geometric data in the form of a point cloud and to depict the existing condition of a building, so that the discrepancies between the two data sets can be identified.
Abstract: With the increased usage of building information models (BIMs) during construction, has BIM become a medium for delivering as-built building information. It is important to maintain accurate and up-to-date information stored in a BIM so that it can become a reliable data source throughout the service life of a facility. Laser scanning technology is able to capture accurate geometric data in the form of a point cloud and to depict the existing condition of a building. Hence, point cloud data captured by laser scans can be used as references to update a given BIM. An important step during the update process is to match segments of elements captured by a point cloud to building components modeled in a BIM, so that the discrepancies between the two data sets can be identified. Typically, features depicted within point cloud segments and BIM components are used in the matching process. However, understanding is limited regarding which features enable the matching process and how these features perform....

19 citations

References
More filters
Journal ArticleDOI
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Abstract: A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing

23,396 citations

Journal ArticleDOI
TL;DR: This paper has designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms.
Abstract: Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on characterizing their performance. In this paper, we present a taxonomy of dense, two-frame stereo methods designed to assess the different components and design decisions made in individual stereo algorithms. Using this taxonomy, we compare existing stereo methods and present experiments evaluating the performance of many different variants. In order to establish a common software platform and a collection of data sets for easy evaluation, we have designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can be easily extended to include new algorithms. We have also produced several new multiframe stereo data sets with ground truth, and are making both the code and data sets available on the Web.

7,458 citations


"Automatic reconstruction of as-buil..." refers background in this paper

  • ...In other fields, such as computer vision, standard test sets and performance metrics have been established [72,83], but no standard evaluation metrics have been established for as-built BIM creation as yet....

    [...]

Journal ArticleDOI
TL;DR: Recognition-by-components (RBC) provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition.
Abstract: The perceptual recognition of objects is conceptualized to be a process in which the image of the input is segmented at regions of deep concavity into an arrangement of simple geometric components, such as blocks, cylinders, wedges, and cones. The fundamental assumption of the proposed theory, recognition-by-components (RBC), is that a modest set of generalized-cone components, called geons (N £ 36), can be derived from contrasts of five readily detectable properties of edges in a two-dimensiona l image: curvature, collinearity, symmetry, parallelism, and cotermination. The detection of these properties is generally invariant over viewing position an$ image quality and consequently allows robust object perception when the image is projected from a novel viewpoint or is degraded. RBC thus provides a principled account of the heretofore undecided relation between the classic principles of perceptual organization and pattern recognition: The constraints toward regularization (Pragnanz) characterize not the complete object but the object's components. Representational power derives from an allowance of free combinations of the geons. A Principle of Componential Recovery can account for the major phenomena of object recognition: If an arrangement of two or three geons can be recovered from the input, objects can be quickly recognized even when they are occluded, novel, rotated in depth, or extensively degraded. The results from experiments on the perception of briefly presented pictures by human observers provide empirical support for the theory. Any single object can project an infinity of image configurations to the retina. The orientation of the object to the viewer can vary continuously, each giving rise to a different two-dimensional projection. The object can be occluded by other objects or texture fields, as when viewed behind foliage. The object need not be presented as a full-colored textured image but instead can be a simplified line drawing. Moreover, the object can even be missing some of its parts or be a novel exemplar of its particular category. But it is only with rare exceptions that an image fails to be rapidly and readily classified, either as an instance of a familiar object category or as an instance that cannot be so classified (itself a form of classification).

5,464 citations


"Automatic reconstruction of as-buil..." refers background in this paper

  • ...Various researchers have proposed candidate sets of primitives, such as geons [9], superquadrics [3], and generalized cylinders [10]....

    [...]

Journal ArticleDOI
TL;DR: Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems.
Abstract: Two of the most critical requirements in support of producing reliable face-recognition systems are a large database of facial images and a testing procedure to evaluate systems. The Face Recognition Technology (FERET) program has addressed both issues through the FERET database of facial images and the establishment of the FERET tests. To date, 14,126 images from 1,199 individuals are included in the FERET database, which is divided into development and sequestered portions of the database. In September 1996, the FERET program administered the third in a series of FERET face-recognition tests. The primary objectives of the third test were to 1) assess the state of the art, 2) identify future areas of research, and 3) measure algorithm performance.

4,816 citations

Proceedings ArticleDOI
01 Aug 1996
TL;DR: This paper presents a volumetric method for integrating range images that is able to integrate a large number of range images yielding seamless, high-detail models of up to 2.6 million triangles.
Abstract: A number of techniques have been developed for reconstructing surfaces by integrating groups of aligned range images. A desirable set of properties for such algorithms includes: incremental updating, representation of directional uncertainty, the ability to fill gaps in the reconstruction, and robustness in the presence of outliers. Prior algorithms possess subsets of these properties. In this paper, we present a volumetric method for integrating range images that possesses all of these properties. Our volumetric representation consists of a cumulative weighted signed distance function. Working with one range image at a time, we first scan-convert it to a distance function, then combine this with the data already acquired using a simple additive scheme. To achieve space efficiency, we employ a run-length encoding of the volume. To achieve time efficiency, we resample the range image to align with the voxel grid and traverse the range and voxel scanlines synchronously. We generate the final manifold by extracting an isosurface from the volumetric grid. We show that under certain assumptions, this isosurface is optimal in the least squares sense. To fill gaps in the model, we tessellate over the boundaries between regions seen to be empty and regions never observed. Using this method, we are able to integrate a large number of range images (as many as 70) yielding seamless, high-detail models of up to 2.6 million triangles.

3,282 citations


"Automatic reconstruction of as-buil..." refers background in this paper

  • ...Non-parametric geometricmodeling reconstructs a surface, typically in the formof a triangle mesh [41], or a volume [18]....

    [...]