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: Three different methods for estimating the original wall surfaces in blast furnaces are introduced, and it is verified whether these methods can appropriately detect scaffolding and wearing regions from point-clouds.
Abstract: Blast furnaces are large industrial structures to produce iron. Since scaffolding and wearing of furnace walls are caused in their long lifecycle, furnaces have to be repeatedly inspected and renov...
2 citations
Cites background from "Automatic reconstruction of as-buil..."
...[11] extracted planes from point-clouds to reconstruct buildings....
[...]
TL;DR: A new tool to assist human operators in the processing of complex scenes obtained from 3D laser scanners in civil engineering applications that can substantially help to reduce the time required to manually process raw scanned data for its subsequent use.
2 citations
08 Mar 2022
TL;DR: A novel method consisting of the regional simplified dual attention network and global graph convolution network is proposed to learn high-dimensional local features in superpoints and progressively update these local embeddings with the recurrent neural network (RNN) network.
Abstract: Point-based networks have been widely used in the semantic segmentation of point clouds owing to the powerful 3D convolution neural network (CNN) baseline. Most of the current methods resort to intermediate regular representations for reorganizing the structure of point clouds for 3D CNN networks, but they may neglect the inherent contextual information. In our work, we focus on capturing discriminative features with the interactive attention mechanism and propose a novel method consisting of the regional simplified dual attention network and global graph convolution network. Firstly, we cluster homogeneous points into superpoints and construct a superpoint graph to effectively reduce the computation complexity and greatly maintain spatial topological relations among superpoints. Secondly, we integrate cross-position attention and cross-channel attention into a single head attention module and design a novel interactive attention gating (IAG)-based multilayer perceptron (MLP) network (IAG–MLP), which is utilized for the expansion of the receptive field and augmentation of discriminative features in local embeddings. Afterwards, the combination of stacked IAG–MLP blocks and the global graph convolution network, called IAGC, is proposed to learn high-dimensional local features in superpoints and progressively update these local embeddings with the recurrent neural network (RNN) network. Our proposed framework is evaluated on three indoor open benchmarks, and the 6-fold cross-validation results of the S3DIS dataset show that the local IAG–MLP network brings about 1% and 6.1% improvement in overall accuracy (OA) and mean class intersection-over-union (mIoU), respectively, compared with the PointNet local network. Furthermore, our IAGC network outperforms other CNN-based approaches in the ScanNet V2 dataset by at least 7.9% in mIoU. The experimental results indicate that the proposed method can better capture contextual information and achieve competitive overall performance in the semantic segmentation task.
2 citations
TL;DR: In this paper , a digital twin model was built in real time with two SLAM methods and then consolidated with the geometric feature extraction methods of fast point feature histograms (FPFH) and fast global registration.
Abstract: The advancement in sensors, robotics, and artificial intelligence has enabled a series of methods such as simultaneous localization and mapping (SLAM), semantic segmentation, and point cloud registration to help with the reality capture process. To completely investigate an unknown indoor space, obtaining a general spatial comprehension as well as detailed scene reconstruction for a digital twin model requires a deeper insight into the characteristics of different ranging sensors, as well as corresponding techniques to combine data from distinct systems. This paper discusses the necessity and workflow of utilizing two distinct types of scanning sensors, including depth camera and light detection and ranging sensor (LiDAR), paired with a quadrupedal ground robot to obtain spatial data of a large, complex indoor space. A digital twin model was built in real time with two SLAM methods and then consolidated with the geometric feature extraction methods of fast point feature histograms (FPFH) and fast global registration. Finally, the reconstructed scene was streamed to a HoloLens 2 headset to create an illusion of seeing through walls. Results showed that both the depth camera and LiDAR could handle a large space reality capture with both required coverage and fidelity with textural information. As a result, the proposed workflow and analytical pipeline provides a hierarchical data fusion strategy to integrate the advantages of distinct sensing methods and to carry out a complete indoor investigation. It also validates the feasibility of robot-assisted reality capture in larger spaces.
2 citations
08 Jun 2022
TL;DR: Terrestrial laser scanning (TLS) has become a powerful, new surveying technology to support a wide range of engineering applications that include topographic mapping, asset management, deformation monitoring, quantity calculations, and safety evaluations as mentioned in this paper .
Abstract: Terrestrial laser scanning (TLS) has become a powerful, new surveying technology to support a wide range of engineering applications that include topographic mapping, asset management, deformation monitoring, quantity calculations, and safety evaluations. This chapter introduces TLS, describes common applications of TLS in Civil Engineering, and provides an overview of several types of TLS systems. The characteristics of TLS systems that differ from other lidar platforms such as airborne and mobile platforms are discussed. A TLS workflow is outlined, focusing on such important steps as planning, field procedures, registration and georeferencing, processing, and analysis. A variety of currently available terrestrial laser scanners are evaluated, and some common limitations, errors, and artifacts in TLS data are identified. Two types of targets to be utilized in scanning are discussed: transformation control targets and validation control targets.
2 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]....
[...]