Authors
Wenpeng Zong, Minglei Li, Xueyong Xiang, Haolong Luo
Published in
Applied optics. Volume 65. Issue 32. Pages 11222-11235. Nov 10, 2026. Epub Oct 12, 2026.
Abstract
As canonical geometric primitives in man-made environments, line features play a pivotal role in terrestrial laser scanner (TLS) point cloud processing and applications. Existing state-of-the-art line extraction methods mainly focus on geometric crease line detection, which fail to capture decorative linear structures without surface geometric discontinuities. To address this gap, this paper proposes a robust high-precision extraction pipeline for image-salient line segments based on unified geometric mapping between 3D TLS point clouds and synchronous digital imagery. First, a decoupled calibration workflow is constructed to realize high-precision alignment between the scanner and external cameras: camera intrinsic parameters are solved via the V-STARS system, and multi-view extrinsic parameters are sequentially estimated using the direct linear transformation (DLT) algorithm. With accurate sensor alignment completed, we derive a closed-form unified mapping model for multi-view images and co-located TLS point clouds. Next, 2D line support regions are detected from optical images, and corresponding 3D supporting point sets are screened through the established mapping relation, followed by robust 3D line fitting to reconstruct image-salient line primitives. Moreover, a 3D point-based normalized cut strategy is introduced to eliminate false line primitives generated in foreground-background overlapping areas. Indoor laboratory and outdoor datasets are adopted for comprehensive verification. Experimental results demonstrate that our method can stably extract image-salient line segments undetectable by pure geometric methods, achieving centimeter-level accuracy (mean deviation below 1 cm) relative to geometric reference lines in both indoor and outdoor scenes.
PMID:
43008148
Bibliographic data and abstract were imported from PubMed on 11 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 8
- Comments 0