Normal vector estimation method for rock mass point clouds with sharp feature preservation via local geometric adjustment

Accurate extraction of rock mass discontinuity parameters is crucial for stability assessment and engineering safety. High-resolution remote sensing facilitates automated extraction, but its effectiveness relies heavily on precise normal estimation to ensure geometric reliability. Conventional methods struggle to preserve sharp features such as edges and corners, thereby reducing accuracy. To address this, we propose a normal estimation method based on local geometric adjustment that enhances feature extraction while maintaining sharp geometries. The approach consists of four steps: (1) classifying points, (2) applying normal and axial projections, (3) fitting segmentation lines via least squares, and (4) refining normals by optimizing local neighborhoods. The proposed method was evaluated on computer-aided design (CAD) models, real objects, and rock mass point clouds, and benchmarked against eight representative algorithms, including principal component analysis (PCA), 2-Jet PCA, Voronoi-based PCA, PCPNet, neural gradient function (NeuralGF), low rank representation (LRR), normal estimation via shifted neighborhood (NSN) and pair consistency voting (PCV). Experimental results demonstrate that our method achieves superior accuracy and efficiency, significantly improving structural plane extraction and ensuring better preservation of sharp geometric features.