Automatic MEP Component Detection with Deep Learning

Kufuor, John; Mohanty, Dibya D.; Valero, Enrique; Bosché, Frédéric

doi:10.1007/978-3-030-68787-8_28

Cited by 6 publications

(4 citation statements)

References 36 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They independently learn complex features, offer a deeper semantic understanding, and efficiently handle large-scale point cloud datasets (Bapat et al, 2023). Some studies focus on nonstructural components (e.g., mechanical and electrical components), and recent reconstruction efforts in deep learning approaches are starting to include indoor object elements (Kufuor et al, 2021). The reference of (Park et al, 2022) presented a technique for indoor object-based point-net deep learning-based 3D model reconstruction.…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%

Leveraging Deep Learning for Automated Reconstruction of Indoor Unstructured Elements in Scan-to-BIM

Mahmoud,

Chen,

Yang

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Achieving automatic 3D reconstruction for indoor scenes is extremely useful in the field of scene understanding. Building information modeling (BIM) models are essential for lowering project costs, assisting in building planning and renovations, as well as improving building management efficiency. However, nearly all current available scan-to-BIM approaches employ manual or semi-automatic methods. These approaches concentrate solely on significant structured objects, neglecting other unstructured elements such as furniture. The limitation arises from challenges in modeling incomplete point clouds of obstructed objects and capturing indoor scene details. Therefore, this research introduces an innovative and effective reconstruction framework based on deep learning semantic segmentation and model-driven techniques to address these limitations. The proposed framework utilizes wall segment recognition, feature extraction, opening detection, and automatic modeling to reconstruct 3D structured models of point clouds with different room layouts in both Manhattan and non-Manhattan architectures. Moreover, it provides 3D BIM models of actual unstructured elements by detecting objects, completing point clouds, establishing bounding boxes, determining type and orientation, and automatically generating 3D BIM models with a parametric algorithm implemented into the Revit software. We evaluated this framework using publicly available and locally generated point cloud datasets with varying furniture combinations and layout complexity. The results demonstrate the proposed framework's efficiency in reconstructing structured indoor elements, exhibiting completeness and geometric accuracy, and achieving precision and recall values greater than 98%. Furthermore, the generated unstructured 3D BIM models keep essential real-scene characteristics such as geometry, spatial locations, numerical aspects, various shapes, and orientations compared to literature methods.

show abstract

Section: Deep Learning-based Approachesmentioning

confidence: 99%

Leveraging Deep Learning for Automated Reconstruction of Indoor Unstructured Elements in Scan-to-BIM

Mahmoud,

Chen,

Yang

et al. 2024

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Yeum et al [61] applied AlexNet [62] to detect the welded joints of a highway sign truss structure. Liang [63] used the faster R-CNN (regions with CNN features) [64] to detect bridge components, while Kufuor et al [65] used it to detect MEP components, including sockets, switches, and radiators, by training both RGB 360 and standard images. Overall, these methods based on R-CNN can achieve high detection accuracy (over 90%) because of the greater availability of labelled data for training.…”

Section: Deep Learning For Shape Detectionmentioning

confidence: 99%

“…Deep learning methods can be generally applied to any object classes, given that there are enough labelled data to train neural networks. Many deep learning methods have been tested in bounding box regression or the PCD semantic and instance segmentation of walls, slabs, doors, windows, columns, beams, or pipes in indoor PCDs, see, e.g., [47,48,65]. These methods can also be applied to the remaining classes of objects; however, there is no scientific evidence of their success.…”

mentioning

confidence: 99%

Construction and Maintenance of Building Geometric Digital Twins: State of the Art Review

Drobnyi

Fathy

et al. 2023

Sensors

View full text Add to dashboard Cite

Most of the buildings that exist today were built based on 2D drawings. Building information models that represent design-stage product information have become prevalent in the second decade of the 21st century. Still, it will take many decades before such models become the norm for all existing buildings. In the meantime, the building industry lacks the tools to leverage the benefits of digital information management for construction, operation, and renovation. To this end, this paper reviews the state-of-the-art practice and research for constructing (generating) and maintaining (updating) geometric digital twins. This paper also highlights the key limitations preventing current research from being adopted in practice and derives a new geometry-based object class hierarchy that mainly focuses on the geometric properties of building objects, in contrast to widely used existing object categorisations that are mainly function-oriented. We argue that this new class hierarchy can serve as the main building block for prioritising the automation of the most frequently used object classes for geometric digital twin construction and maintenance. We also draw novel insights into the limitations of current methods and uncover further research directions to tackle these problems. Specifically, we believe that adapting deep learning methods can increase the robustness of object detection and segmentation of various types; involving design intents can achieve a high resolution of model construction and maintenance; using images as a complementary input can help to detect transparent and specular objects; and combining synthetic data for algorithm training can overcome the lack of real labelled datasets.

show abstract

“…The Faster R-CNN (Girshick, 2015) uses the convolutional network to directly generate candidate regions. It has been applied to detect building electrical instances by training both RGB 360° and standard images (Kufuor et al, 2021). However, this method can only locate the instance position with bounding box.…”

Section: Image-based Instance Detectionmentioning

confidence: 99%

Geometry updating for digital twins of buildings: a review to derive a new geometry-based object class hierarchy

Hu¹,

Fathy²,

Ioannis³

2022

Proceedings of the 2022 European Conference on Computing in Construction

View full text Add to dashboard Cite

Geometry updating for digital twins of buildings is a timeconsuming and manual task, resulting in poor progress monitoring and quality control during the construction stage. This paper reviews the state of the art in practice and research on spatial and visual data-based approaches for updating digital twin geometry of buildings. We draw novel key insights into the effectiveness, experiments, and limitations of seven classes of methods summarised from the most recent papers. Consequently, four core gaps in knowledge are investigated. Finally, a new geometrybased object class hierarchy is derived to support geometry updating for maintaining digital twins in future directions.

show abstract

Automatic MEP Component Detection with Deep Learning

Cited by 6 publications

References 36 publications

Leveraging Deep Learning for Automated Reconstruction of Indoor Unstructured Elements in Scan-to-BIM

Leveraging Deep Learning for Automated Reconstruction of Indoor Unstructured Elements in Scan-to-BIM

Construction and Maintenance of Building Geometric Digital Twins: State of the Art Review

Geometry updating for digital twins of buildings: a review to derive a new geometry-based object class hierarchy

Contact Info

Product

Resources

About