Weakly supervised semantic segmentation of 3D point clouds for coal mine roadways: method and application

Abstract

With advantages in robustness to variations in ambient illumination and active sensing, light detection and ranging has become a primary modality for environmental perception in underground coal mines characterized by inadequate illumination and high dust concentrations. However, raw point clouds lack semantic attributes, which limits their direct application in scene understanding for digital mines. Although fully supervised deep learning methods for point cloud semantic segmentation achieve high performance, they rely heavily on labor-intensive point-wise annotations, incurring high costs and potential human error. To address this, this paper proposes a weakly supervised semantic segmentation framework specifically designed for coal mine roadways. The framework establishes a comprehensive workflow spanning from data acquisition to sparse-supervised training. By leveraging sparse labels to drive model optimization, the method maintains segmentation performance while significantly reducing annotation costs, achieving a trade-off between engineering precision and deployment overhead. Experimental results demonstrate that using only 0.1% sparse annotations, the proposed method achieves an overall accuracy of 91.64% and a mean intersection over union of 78.83%. Compared to fully supervised models, it reduces the annotation time by a factor of 2–3 times improvement in annotation efficiency with a precision loss of approximately 7%. The segmented structural point clouds are utilized for roadway deformation monitoring and parametric geometric reconstruction. This supports a comprehensive digital twin framework that enables high-fidelity modeling and early warning of centimeter-scale deformation. This research confirms that the proposed technology provides a cost-effective and efficient path for scene understanding in intelligent mines, demonstrating practical value and potential for practical deployment.