Abstract. Current heritage analysis applications and documentation techniques for timber roof structures rely on manual measurements to provide the spatial data. Major simplifications are made to document these structures efficiently. However, these simplified geometric models provide less reliable results. Therefore, the need exists for more realistic models. Additionally, the exchangeability of information between varying parties is paramount. Hence, the construction elements should be defined in a Building Information Model (BIM). This allows users to reuse the model, allowing the distribution of information throughout the project. The goal of our research is to create a realistic BIM model of a complex heritage roof structure employing dense point clouds. The comparison of our complex geometric model to a traditional wire-frame model proves that our approach provides more reliable results in terms of geometry and structural behaviour. Our work covers the acquisition, the modelling and the structural analysis of timber roof structures.
ABSTRACT:Semantically rich three dimensional models such as Building Information Models (BIMs) are increasingly used in digital heritage. They provide the required information to varying stakeholders during the different stages of the historic buildings life cyle which is crucial in the conservation process. The creation of as-built BIM models is based on point cloud data. However, manually interpreting this data is labour intensive and often leads to misinterpretations. By automatically classifying the point cloud, the information can be proccesed more effeciently. A key aspect in this automated scan-to-BIM process is the classification of building objects. In this research we look to automatically recognise elements in existing buildings to create compact semantic information models. Our algorithm efficiently extracts the main structural components such as floors, ceilings, roofs, walls and beams despite the presence of significant clutter and occlusions. More specifically, Support Vector Machines (SVM) are proposed for the classification. The algorithm is evaluated using real data of a variety of existing buildings. The results prove that the used classifier recognizes the objects with both high precision and recall. As a result, entire data sets are reliably labelled at once. The approach enables experts to better document and process heritage assets.
The automated reconstruction of Building Information Modeling (BIM) objects from point cloud data is still subject of ongoing research. A vital step in the process is identifying the observations for each wall object. Given a set of segmented and classified point clouds, the labeled segments should be clustered according to their respective objects. The current processes to perform this task are sensitive to noise, occlusions, and the associativity between faces of neighboring objects. The proper retrieval of the observed geometry is especially important for wall geometry as it forms the basis for further BIM reconstruction. In this work, a method is presented to automatically group wall segments derived from point clouds according to the proper walls of a building. More specifically, a Conditional Random Field is employed that evaluates the context of each wall segment in order to determine which wall it belongs to. First, a set of classified planar primitives is obtained through algorithms developed in prior work. Next, both local and contextual features are extracted based on the nearest neighbors and a number of seeds that are heuristically determined. The final wall clusters are then computed by decoding the graph. The method is tested on our own data as well as the 2D-3D-Semantics (2D-3D-S) benchmark data of Stanford. Compared to a conventional region growing method, the proposed method reduces the rate of false positives, resulting in better wall clusters. Overall, the method computes a more balanced clustering of the observations. A key advantage of the proposed method is its capability to deal with wall geometry in complex configurations in multi-storey buildings opposed to the presented methods in current literature.
Point cloud segmentation is a crucial step in scene understanding and interpretation. The goal is to decompose the initial data into sets of workable clusters with similar properties. Additionally, it is a key aspect in the automated procedure from point cloud data to BIM. Current approaches typically only segment a single type of primitive such as planes or cylinders. Also, current algorithms suffer from oversegmenting the data and are often sensor or scene dependent.<br><br> In this work, a method is presented to automatically segment large unstructured point clouds of buildings. More specifically, the segmentation is formulated as a graph optimisation problem. First, the data is oversegmented with a greedy octree-based region growing method. The growing is conditioned on the segmentation of planes as well as smooth surfaces. Next, the candidate clusters are represented by a Conditional Random Field after which the most likely configuration of candidate clusters is computed given a set of local and contextual features. The experiments prove that the used method is a fast and reliable framework for unstructured point cloud segmentation. Processing speeds up to 40,000 points per second are recorded for the region growing. Additionally, the recall and precision of the graph clustering is approximately 80%. Overall, nearly 22% of oversegmentation is reduced by clustering the data. These clusters will be classified and used as a basis for the reconstruction of BIM models.
ABSTRACT:The use of Building Information Modeling (BIM) for existing buildings based on point clouds is increasing. Standardized geometric quality assessment of the BIMs is needed to make them more reliable and thus reusable for future users. First, available literature on the subject is studied. Next, an initial proposal for a standardized geometric quality assessment is presented. Finally, this method is tested and evaluated with a case study. The number of specifications on BIM relating to existing buildings is limited. The Levels of Accuracy (LOA) specification of the USIBD provides definitions and suggestions regarding geometric model accuracy, but lacks a standardized assessment method. A deviation analysis is found to be dependent on (1) the used mathematical model, (2) the density of the point clouds and (3) the order of comparison. Results of the analysis can be graphical and numerical. An analysis on macro (building) and micro (BIM object) scale is necessary. On macro scale, the complete model is compared to the original point cloud and vice versa to get an overview of the general model quality. The graphical results show occluded zones and non-modeled objects respectively. Colored point clouds are derived from this analysis and integrated in the BIM. On micro scale, the relevant surface parts are extracted per BIM object and compared to the complete point cloud. Occluded zones are extracted based on a maximum deviation. What remains is classified according to the LOA specification. The numerical results are integrated in the BIM with the use of object parameters.
Interpreting 3D point cloud data of the interior and exterior of buildings is essential for automated navigation, interaction and 3D reconstruction. However, the direct exploitation of the geometry is challenging due to inherent obstacles such as noise, occlusions, sparsity or variance in the density. Alternatively, 3D mesh geometries derived from point clouds benefit from preprocessing routines that can surmount these obstacles and potentially result in more refined geometry and topology descriptions. In this article, we provide a rigorous comparison of both geometries for scene interpretation. We present an empirical study on the suitability of both geometries for the feature extraction and classification. More specifically, we study the impact for the retrieval of structural building components in a realistic environment which is a major endeavor in Building Information Modeling (BIM) reconstruction. The study runs on segment-based structuration of both geometries and shows that both achieve recognition rates over 75% F1 score when suitable features are used.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.