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
TL;DR: The empirical comparison of both strategies has promising results towards the reconstruction of wall geometry of multi-story buildings and showcases the fundamental differences in both strategies and will support the further development of these methods.
Abstract: As-built Building Information Models (BIMs) are becoming increasingly popular in the Architectural, Engineering, Construction, Owner and Operator (AECOO) industry. These models reflect the state of the building up to as-built conditions. The production of these models for existing buildings with no prior BIM includes the segmentation and classification of point cloud data and the reconstruction of the BIM objects. The automation of this process is a must since the manual Scan-to-BIM procedure is both time-consuming and error prone. However, the automated reconstruction from point cloud data is still ongoing research with both 2D and 3D approaches being proposed. There currently is a gap in the literature concerning the quality assessment of the created entities.
In this research, we present the empirical comparison of both strategies with respect to existing specifications. A 3D and a 2D reconstruction method are implemented and tested on a real life test case. The experiments focus on the reconstruction of the wall geometry from unstructured point clouds as it forms the basis of the model. Both presented approaches are unsupervised methods that segment, classify and create generic wall elements. The first method operates on the 3D point cloud itself and consists of a general approach for the segmentation and classification and a class-specific reconstruction algorithm for the wall geometry. The point cloud is first segmented into planar clusters, after which a Random Forests classifier is used with geometric and contextual features for the semantic labelling. The final wall geometry is created based on the 3D point clusters representing the walls. The second method is an efficient Manhattan-world scene reconstruction algorithm that simultaneously segments and classifies the point cloud based on point feature histograms. The wall reconstruction is considered an instance of image segmentation by representing the data as 2D raster images. Both methods have promising results towards the reconstruction of wall geometry of multi-story buildings. The experiments report that over 80% of the walls were correctly segmented by both methods. Furthermore, the reconstructed geometry is conform Level-of-Accuracy 20 for 88% of the data by the first method and for 55% by the second method despite the Manhattan-world scene assumption. The empirical comparison showcases the fundamental differences in both strategies and will support the further development of these methods.
19 citations
Cites background or methods from "Automatic reconstruction of as-buil..."
...Moreover, the existing documentation often does not match the as-design model of the building due to construction changes or renovations (Brilakis et al., 2010; Patraucean et al., 2015; Tang et al., 2010)....
[...]
...A common technique used in building surveying is Terrestrial Laser Scanning (TLS) (Tang et al., 2010; Bassier et al., 2016)....
[...]
TL;DR: A review of the representative technologies applied to construction-project-progress data collection and identified the unique characteristics of each technology confirmed that the technical limitations of the construction progress tracking through the point cloud do not exist, and that a fairly high degree of progress data which contains efficiency and accuracy can be collected.
Abstract: Compared to the past, the complexity of construction-project progress has increased as the size of structures has become larger and taller. This has resulted in many unexpected problems with an increasing frequency of occurrence, such as various uncertainties and risk factors. Recently, research was conducted to solve the problem via integration with data-collection automation tools of construction-project-progress measurement. Most of the methods used spatial sensing technology. Thus, this study performed a review of the representative technologies applied to construction-project-progress data collection and identified the unique characteristics of each technology. The basic principle of the progress proposed in this study is its execution through the point cloud and the attributes of BIM, which were studied in five stages: (1) Acquisition of construction completion data using a point cloud, (2) production of a completed 3D model, (3) interworking of an as-planned BIM model and as-built model, (4) construction progress tracking via overlap of two 3D models, and (5) verification by comparison with actual data. This has confirmed that the technical limitations of the construction progress tracking through the point cloud do not exist, and that a fairly high degree of progress data which contains efficiency and accuracy can be collected.
19 citations
13 May 2014
TL;DR: In this paper, a method to automatically create as-is 3D building models automatically from an unorganized point cloud collected by a 3D laser scanner is introduced, where the collected raw data are downsized and segmented to individual plane segments.
Abstract: Building information models (BIMs) increasingly are applied throughout a building's life cycle for various applications, such as building renovation, energy simulation, and performance analysis in the architecture, engineering construction, and facility management (AEC/FM) domain. In a traditional approach, as-is BIM is primarily manually created from point clouds, which is labor intensive, costly, and time consuming. This paper introduces a method to create as-is 3D building models automatically from an unorganized point cloud collected by a 3D laser scanner. The collected raw data are downsized and segmented to individual plane segments. Then, boundary estimation method and building component recognition methods are applied to recognize all building components as individual objects and visualize them as polygons. The proposed method was tested on outdoor point cloud data to validate its feasibility and evaluate its performance. The analyzed results showed that the proposed method would simplify and accelerate the as-is building model creation process.
18 citations
TL;DR: In this paper, a new methodology in Experimental Archaeology is proposed; it proved to be original and innovative in the examination of the buried building, taking advantage of technologies focused on the architectural reliability validated by inferred digital models.
Abstract: The digital reconstruction of the recently discovered Tuscanic temple of Uni in Marzabotto gave the chance to test the application of the Building Information Modeling (BIM) process to the combined fields of Archaeology and Engineering. In addition to the traditional historic and archaeological analysis, a new methodology in Experimental Archaeology is proposed; it proved to be original and innovative in the examination of the buried building, taking advantage of technologies focused on the architectural reliability validated by inferred digital models. The peculiar aspect of the research involves the elements at the beginning of the process, which consist of foundations or negative archaeological evidences only, supported by the clues and the rules that can be found in the historic and scientific literature. To better define this distinctive working process, the expression ArchaeoBIM was proposed, which highlights the common BIM matrix used for the data management through one or more analytical models, applied to the peculiar aspects of the Archaeological discipline.
18 citations
TL;DR: In this paper , a semantic-aided change detection method aimed at monitoring construction progress using UAV-based photogrammetric point clouds is presented. But the method is limited to the detection of geometric and semantic changes.
18 citations
References
More filters
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
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....
[...]
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]....
[...]
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
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]....
[...]