NRLC增强的两阶段DBSCAN聚类的岩石不连续面识别方法
By using the NRLC-enhanced two-stage DBSCAN clustering method, concave, convex, and boundary feature points in rock point clouds are identified. Combined with DBSCAN clustering, the problems of low efficiency, insufficient information, and noise interference in traditional methods are solved, achieving efficient and accurate identification of rock discontinuities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV OF SCI & TECH
- Filing Date
- 2025-11-03
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional methods for identifying discontinuous rock surfaces are inefficient, have limited sampling range, struggle to acquire three-dimensional spatial information, and suffer from complex point cloud data processing and severe noise interference, which affects identification accuracy.
A two-stage DBSCAN clustering method enhanced by NRLC is adopted. First, concave, convex and boundary feature points in the rock point cloud are identified. The normal vector is calculated by local fitting. The DBSCAN clustering is combined to identify the cluster and individual discontinuities.
It improves recognition efficiency, acquires more comprehensive spatial information, reduces computational complexity, improves fitting accuracy and recognition accuracy, and can quickly process large-scale point cloud data.
Smart Images
Figure CN121582773B_ABST