A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Learning-guided point cloud vectorization for building component modeling
Abstract This study presents a novel learning-guided point cloud vectorization to form the vector models of building components. To this end, two learning-based models are modified to realize feature detection and vectorization. The learning-guided scheme can comprehend the definition and mutual relationships of object vertices by learning through existing BIM models and thus predict the vector model of newly given point clouds consequently. Moreover, the effectiveness was verified by using point clouds under different quality levels. The quantitative indices showed promising results, in which the accuracy of object vertex positions achieved 10 cm in beam and column categories and less than 25 cm for all building components. On the other hand, the vertex connections of the vector models reported accuracy above 70%. Therefore, the results can be deemed as fundamental models to improve the automation performance of further refinements or subsequent value-added applications.
Highlights A learning-guided scheme for facilitating scan-to-BIM processing. Dedicate to explore object vertex detection and connection for point cloud vectorization. 3D training data acquisition and labeling are realized by leveraging BIM models into the framework. A 2D graph network is modified to predict 3D vertex connections of objects.
Learning-guided point cloud vectorization for building component modeling
Abstract This study presents a novel learning-guided point cloud vectorization to form the vector models of building components. To this end, two learning-based models are modified to realize feature detection and vectorization. The learning-guided scheme can comprehend the definition and mutual relationships of object vertices by learning through existing BIM models and thus predict the vector model of newly given point clouds consequently. Moreover, the effectiveness was verified by using point clouds under different quality levels. The quantitative indices showed promising results, in which the accuracy of object vertex positions achieved 10 cm in beam and column categories and less than 25 cm for all building components. On the other hand, the vertex connections of the vector models reported accuracy above 70%. Therefore, the results can be deemed as fundamental models to improve the automation performance of further refinements or subsequent value-added applications.
Highlights A learning-guided scheme for facilitating scan-to-BIM processing. Dedicate to explore object vertex detection and connection for point cloud vectorization. 3D training data acquisition and labeling are realized by leveraging BIM models into the framework. A 2D graph network is modified to predict 3D vertex connections of objects.
Learning-guided point cloud vectorization for building component modeling
Chuang, Tzu-Yi (author) / Sung, Cheng-Che (author)
2021-09-24
Article (Journal)
Electronic Resource
English
Cache-efficient renumbering for vectorization
| British Library Online Contents | 2010
Vectorization Using a Personal Computer
| British Library Conference Proceedings | 1995
Vectorization method of jacquard image
| British Library Online Contents | 2006