CPMLP: a novel approach for semantic segmentation of open-pit mining point clouds

Abstract As the demand for multi-scenario semantic updates in intelligent open-pit mining grows, existing semantic segmentation techniques encounter substantial challenges, particularly in handling visually indistinguishable, continuous geometric engineering objects. These approaches frequently fall short of meeting the accuracy standards required for practical applications. To tackle this challenge, the present study introduces a novel semantic segmentation method, CAD-to-PC matching and label propagation (CPMLP). The method constructs unified graph representations from 2D computer-aided design (CAD) drawings and 3D point clouds (PCs), extracts subgraph features using a graph-based feature encoding module, performs cross-graph alignment through contrastive learning, and propagates semantic labels from CAD to PC nodes. Experimental results demonstrate that CPMLP achieves high segmentation accuracy, with an average 3D mean Intersection over Union of approximately 0.7 across different acquisition routes, and robust generalization within complex mining environments. The proposed method provides a feasible solution for high-precision semantic segmentation in intelligent mining scenarios.