机载激光点云露天矿特征地物提取方法及系统
By identifying candidate feature points of step lines in airborne laser point cloud data of open-pit mines, and combining spatial correlation and local neighborhood feature calculation, coded features are generated and feature diffusion and fusion are performed. This solves the efficiency and accuracy problems in feature feature extraction in open-pit mines and achieves efficient and accurate automatic feature feature extraction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 北京捷翔天地信息技术有限公司
- Filing Date
- 2026-01-20
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are computationally inefficient in extracting feature features in open-pit mines, making it difficult to achieve high-efficiency automation. Furthermore, they lack sufficient recognition accuracy under complex terrain conditions and cannot adapt to the terrain characteristics of different mining areas.
Candidate feature points for step lines are identified by a joint criterion based on the plane fitting residual and the dispersion of the normal vector angle. Curve fitting is performed and step line fitting results are generated recursively. Combined with spatial correlation and local neighborhood feature vector calculation, encoded features are generated and interpolation diffusion and hierarchical feature fusion are performed to extract target ground features.
It improves the accuracy and robustness of feature extraction, adapts to the complex terrain of open-pit mines, and achieves efficient and accurate automatic extraction of features and features, ensuring the integrity and accuracy of the extraction results.
Smart Images
Figure CN121937918B_ABST