scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Classification of sensor independent point cloud data of building objects using random forests

TL;DR: A generic approach to automatically identify structural elements for the purposes of Scan-to-BIM by taking a set of planar primitives that are pre-segmented from the point cloud.
Abstract: The Architectural, Engineering and Construction (AEC) industry is looking to integrate Building Information Modeling (BIM) for existing buildings. Currently these as-built models are created manually, which is time-consuming. An important step in the automated Scan-to-BIM procedure is the interpretation and classification of point cloud data. This is computationally challenging due to the sheer size of point cloud data for an entire building. Additionally, the variety of objects makes classification problematic. Existing methods integrate prior knowledge from the sensors or environment to improve the results. However, these approaches are therefore often case specific and thus have limited applicability. The goal of this research is to provide a method that is independent of any sensor or scene within a building environment. Furthermore, our method processes the entire building simultaneously, resulting in more distinct local and contextual features. This paper presents a generic approach to automatically identify structural elements for the purposes of Scan-to-BIM. More specifically, a Random Forests classifier is employed for the classification of the floors, ceilings, roofs, walls and beams. As input, our algorithm takes a set of planar primitives that are pre-segmented from the point cloud. This significantly reduces the data while maintaining accuracy. Both contextual and geometric features are used to describe the observed patches. The algorithm is evaluated using realistic data for a wide variety of existing buildings including houses, school facilities, a factory, a castle and a church. The experiments prove that the proposed algorithm is capable of properly labeling 87% of the structural elements with an average precision of 85% in highly cluttered environments without the support of the sensors position. In future work, the classified patches will be processed by class-specific reconstruction algorithms to create BIM geometry.

Summary (2 min read)

1. Introduction

  • The implementation of Building Information Modelling (BIM) for existing buildings is gaining popularity.
  • Experiencing the advantage of BIM for new constructions, the industry now looks to implement as-built BIM.
  • These as-built models store an immense amount of information about a building at the varying stages of the construction’s life cycle [1].
  • More specifically, structural elements such as floors, ceilings, roofs, walls and beams are automatically identified in existing structures.
  • 35 In Section 4 the methodology is presented.

2. Background

  • The procedure of converting point cloud data to BIM geometry is referred40 to as Scan-to-BIM.
  • Second, each cluster is provided with a class label.
  • Examples of local geometric features are the area, surface dimensions and orientation.
  • Heuristic models are based on user defined rules in a certain structure.
  • Alternatively, machine learning algorithms are60 employed such as Discriminant Analysis (DA), Decision Trees, Support Vector Machines (SVM), Neural Networks (NN), Probabilistic Graphical Models (PGM), etc. [8, 12, 13, 16, 17, 18, 19].

4.2. Model formulation

  • Each tree consists of a series of binary splits that separate the input variables.
  • The Random Forests model is trained using leave-p-out cross validation.
  • This intuitive procedural programming platform allows for flexible data processing and evaluation.
  • The classified patches are exported to the Rhinoceros model space for185 validation and further processing.

5. Experiments

  • 10 structures including houses, offices, industrial buildings and churches were used for training and testing (Fig 5).
  • The test sites were acquired under realistic conditions including clutter, occlusions, traffic, etc.
  • Ghz with 4 cores and 4 hyperthreads and 32GB RAM.
  • Over 90,000 surfaces were computed for the projects.
  • All 17 predictors from table 1 were considered for the classification of the observations.

5.1. Performance

  • The classification results are depicted in the confusion matrices in Fig.7.
  • This is very accurate given the large variety of buildings and objects that were evaluated.
  • Increased confusion rates are observed between the walls and clutter classes as well as the ceiling and roof classes.
  • This is due to the fact that several data sets do not have roofs making the top ceilings harder to230 interpret (Fig.8b).
  • Several misclassifications are due to their sensor independent approach.

5.2. Comparison

  • The authors compared the results of the Random Forests classifier with other common machine learning methods.
  • Table 2 depicts the results of the model performance for K-Nearest Neighbours (KNN), a multiceptron Neural Network (NN), Support Vector Machines (SVM) and boosted decision trees.
  • All models240 were tested with the same predictors and data as the proposed model.
  • This proves that the used predictors are both distinct and robust for the detection of structural elements in cluttered and noisy environments.
  • Since their approach focusses on post-processing applications, the training time is of lesser concern.

6. Discussion and Conclusion

  • More specifically, the data is pre-segmented and processed by machine learning algorithms to label the floors, ceilings, roofs, beams, walls and clutter in noisy and occluded environ-255 ments.
  • This allows for the processing of larger data sets and provides additional features.
  • Some classes underperform due to the large variance in feature values within the265 class.
  • This will enhance the current classification and allows for the processing of non-planar classes such as cylindrical beams280 and pipes as well as furniture.

Did you find this useful? Give us your feedback

Figures (10)
Citations
More filters
Journal ArticleDOI
TL;DR: An unsupervised method that procedurally models the geometry of the walls based on point cloud data is presented to automatically reconstruct as-built BIM for generic buildings and shows promising results to reliably and accurately create as- built models.
Abstract: . The reconstruction of Building Information Modeling objects for as-built modeling is currently the subject of ongoing research. A popular method is to extract structure information from point cloud data to create a set of parametric objects. This requires the interpretation of the point cloud data which currently is a manual and labor intensive procedure. Automated processes have to cope with excessive occlusions and clutter in the data sets. To create an as-built BIM, it is vital to reconstruct the building’s structure i.e. wall geometry prior to the reconstruction of other objects. In this work, a novel method is presented to automatically reconstruct as-built BIM for generic buildings. We presented an unsupervised method that procedurally models the geometry of the walls based on point cloud data. A bottom-up process is defined where consecutively higher level information is extracted from the point cloud data using pre-trained machine learning models. Prior to the reconstruction, the data is segmented, classified and clustered to retrieve all the available observations of the walls. The resulting geometry is processed by the reconstruction algorithm. First, the necessary information is extracted from the observations for the creation of parametric solid objects. Subsequently, the final walls are created by updating their topology. The method is tested on a variety of scenes and shows promising results to reliably and accurately create as-built models. The accuracy of the generated geometry is similar to the precision of expert modelers. A key advantage is that that the algorithm creates Revit and Rhino native objects which makes the geometry directly applicable to a wide range of applications.

6 citations


Cites methods from "Classification of sensor independen..."

  • ...A pre-trained Random Forests model is used for the classification (Bassier et al., 2018)....

    [...]

  • ...This research solely discuses the final step as the first three steps are performed in prior work (Bassier et al., 2018, Bassier and Vergauwen, 2019b)....

    [...]

Journal ArticleDOI
TL;DR: The developed methodology for detecting aviation obstacles consists of three main stages: point cloud filtration based on height–preliminary identification of aviation obstacles, followed by 3D point cloud segmentation using a modified RANSAC algorithm, supplemented with two-dimensional vector data of Aviation obstacles to improve the accuracy of the segmentation process.
Abstract: Currently, more and more accurate data provided by UAVs make it possible to analyze land cover, which requires the detection of objects and their individual elements. Object detection and determination of their geometric features is possible thanks to dense point clouds generated based on imagery obtained from low altitudes. 3D data from UAVs turn out to be extremely useful for ensuring safety in the airspace in the close vicinity of the airport. This article presents the methodology of automatic aviation obstacle detection based on low altitude data (UAV). The research was carried out on a dense 3D point cloud. The developed methodology for detecting aviation obstacles consists of three main stages. The first is point cloud filtration based on height–preliminary identification of aviation obstacles, followed by 3D point cloud segmentation using a modified RANSAC algorithm, supplemented with two-dimensional vector data of aviation obstacles to improve the accuracy of the segmentation process. The last stage is the classification of aviation obstacles according to the adopted height and cross-section criterion. The proposed method of detecting aviation obstacles is characterized by high accuracy. The mean error of fitting the point cloud to the obstacle database ranged from ± 0.04 m to ± 0.07 m.

5 citations

Journal ArticleDOI
TL;DR: Wang et al. as mentioned in this paper proposed a new DL framework, with the capability of establishing squeeze-excite (SE) mechanism in local aggregation operators and exploiting deep residual learning for point cloud learning, to help classify complex piping components more efficiently and robustly.

4 citations

Book ChapterDOI
29 Oct 2018
TL;DR: This paper presents two workflows for increasing the automation in HBIM generation that are closer to semi-automated modelling since some manual operations are still needed and is implemented as a Revit Plug-in and for this reason it is more user-friendly.
Abstract: In the last years creation of as-built Building Information Modelling (BIM), and Historic Building Information Modelling (HBIM) in particular, has become a widely researched topic. In particular, the so-called “Scan.-to-BIM” procedure has received a lot of attention. This is mainly given by the fact that nowadays, terrestrial laser scanning (TLS), either static and mobile, and 3D photogrammetry are quite popular techniques to acquire building geometry raw data. However, turning a set of scans into a BIM model is still a labor-intensive and manual work. This paper presents two workflows for increasing the automation in HBIM generation. The presented approaches differ in the level of automation achieved and in the level of maturity. Indeed, while the first one presents a higher level of automation it is designed only to work in the case straight geometrical features are dominant in the scene (i.e., Manhattan world assumption holds). In addition, it is currently implemented in Matlab. On the other hand, the second one is closer to semi-automated modelling since some manual operations are still needed. However, it is implemented as a Revit Plug-in and for this reason it is more user-friendly.

4 citations

Proceedings ArticleDOI
01 Jan 2019
TL;DR: The capabilities of the information structures found in IFCs to be used as data sources for developing machine learning predictive models, will be examined and their suitability for predicting – through such machine learning models – the delivery cost and time overheads of a construction project will be considered.
Abstract: Qualitative and quantitative data are important in construction management. However, despite the capabilities of construction informatics, such data and its sources have scarcely been fully and systematically utilized for predictive purposes. Building Information Models (BIM) are such a data source. Within BIM, information structures enabling interoperability and providing utilizable data throughout the various Levels of Development (LODs) of a building – for example, Industry Foundation Classes (IFCs) – can be fully and meaningfully exploited through data mining, and more particularly, via machine learning. In this paper, the capabilities of the information structures found in IFCs to be used as data sources for developing machine learning predictive models, will be examined. In addition, and by conceptually tying such data with constructability, their suitability for predicting – through such machine learning models – the delivery cost and time overheads of a construction project, will be considered.

3 citations


Cites methods from "Classification of sensor independen..."

  • ...through the classification of apartment rooms [46], heritage buildings [47], sensor-independent point cloud data as part of the scan-to-BIM process [48],...

    [...]

References
More filters
Journal ArticleDOI
01 Oct 2001
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.

79,257 citations

Book
01 Oct 2004
TL;DR: Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts, and discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining.
Abstract: The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. In order to present a unified treatment of machine learning problems and solutions, it discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining. All learning algorithms are explained so that the student can easily move from the equations in the book to a computer program. The text covers such topics as supervised learning, Bayesian decision theory, parametric methods, multivariate methods, multilayer perceptrons, local models, hidden Markov models, assessing and comparing classification algorithms, and reinforcement learning. New to the second edition are chapters on kernel machines, graphical models, and Bayesian estimation; expanded coverage of statistical tests in a chapter on design and analysis of machine learning experiments; case studies available on the Web (with downloadable results for instructors); and many additional exercises. All chapters have been revised and updated. Introduction to Machine Learning can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods. Adaptive Computation and Machine Learning series

3,950 citations

Book ChapterDOI
01 Jan 2019
TL;DR: Machine learning is evolved from a collection of powerful techniques in AI areas and has been extensively used in data mining, which allows the system to learn the useful structural patterns and models from training data as discussed by the authors.
Abstract: Machine learning is evolved from a collection of powerful techniques in AI areas and has been extensively used in data mining, which allows the system to learn the useful structural patterns and models from training data Machine learning algorithms can be basically classified into four categories: supervised, unsupervised, semi-supervised and reinforcement learning In this chapter, widely-used machine learning algorithms are introduced Each algorithm is briefly explained with some examples

1,668 citations

Journal ArticleDOI
TL;DR: Results show scarce BIM implementation in existing buildings yet, due to challenges of (1) high modeling/conversion effort from captured building data into semantic BIM objects, (2) updating of information in BIM and (3) handling of uncertain data, objects and relations in B IM occurring inexisting buildings.

1,499 citations

Journal ArticleDOI
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.

789 citations

Frequently Asked Questions (2)
Q1. What contributions have the authors mentioned in the paper "Classification of sensor independent point cloud data of building objects using random forests" ?

The goal of this research is to provide a method that is sensor independent and labels entire buildings at once. This paper presents a method to automatically identify structural elements for the purposes of Scan-to-BIM. The experiments prove that the proposed algorithm is capable of labelling structural elements with reported precisions of 85 % and 87 % recall in highly cluttered environments. 

In future work, the method will be investigated further to improve the labelling performance. Also, research will be performed towards the integration of probabilistic graphical models to increase the methods perfor- mance.