The large-scale point cloud data representing buildings should be prudently pre-processed and down-sampled prior to post-data processing activities, such as data segmentation or classification and indoor scene analysis, and visualization of the processed results as three-dimensional (3D) digital models. However, current pre-processing tasks and down-sampling procedures encountered the challenge of preserving the geometric and semantic features of the scanned object and contributing to accurate 3D reconstruction due to the loss of significant features on buildings. Therefore, this paper proposed a framework that pre-processes unstructured laser scanning data to optimize the efficiency of data processing activities and the accuracy of the produced output, i.e., reconstructed 3D building models. The pre-processing framework includes building the topology of the unstructured dataset, down-sampling the raw data through an improved voxel-based approach, and performing indoor scene analysis such as normal estimation, point alignment, and data classification. The experimental results verified that the proposed framework efficiently pre-processes the input data and preserves the geometric characteristics of the digital models with high accuracy, thereby supporting reliable 3D reconstruction for various applications.
Optimal Pre-processing of Laser Scanning Data for Indoor Scene Analysis and 3D Reconstruction of Building Models
KSCE J Civ Eng
KSCE Journal of Civil Engineering ; 28 , 1 ; 1-14
2024-01-01
14 pages
Article (Journal)
Electronic Resource
English
Interactive Indoor Scene Reconstruction from Image Mosaics Using Cuboid Structure
British Library Conference Proceedings | 2002
|British Library Conference Proceedings | 1997
|Collision Reconstruction Techniques: Collision Scene Analysis
British Library Conference Proceedings | 1985
|