光学精密工程2025，Vol.33Issue(16)：2602-2615,14.DOI:10.37188/OPE.20253316.2602
多视角下多特征融合的三维局部特征描述符
3D local feature descriptor based on multi-view geometric distribution signatures
摘要
Abstract
To address the problem of incomplete description of local surface geometric features by existing handcrafted descriptors,this paper proposed a high-discriminative and robust multi-view geometric distri-bution signature(MGDS).First,a local reference frame(LRF)was constructed based on the keypoints and their neighboring points.The local surface was voxelized.The centroid distribution of the 3D voxels,the contour features of 2D sectors,the point density distribution of 2D grid,and the depth fluctuation of the surface were calculated to generate the geometric feature descriptor.Next,the local surface was rotat-ed multiple times based on the LRF to generate new shape representations.The rotated surfaces were en-coded using centroid,contour point,density,and z-value fluctuation information.By capturing these geo-metric feature descriptors from multiple viewpoints and concatenating them into a single feature vector,the final multi-view geometric distribution signature(MGDS)was obtained.Experiments are conducted on four datasets:RandomView,SpaceTime,Kinect,and B3R with different Gaussian noise and grid resolu-tions.The proposed MGDS descriptor is compared with ten existing descriptors.Compared to other de-scriptors,MGDS descriptors outperform existing local feature descriptors.Experimental results indicate that the proposed MGDS descriptor exhibits good descriptiveness and robustness,making it suitable for ac-curate registration of 3D point cloud.关键词
点云/局部特征描述符/多视角特征/多特征融合/特征匹配Key words
point cloud/local feature descriptor/multi-view features/multi-feature fusion/feature matching分类
信息技术与安全科学引用本文复制引用
郝雯,魏海南..多视角下多特征融合的三维局部特征描述符[J].光学精密工程,2025,33(16):2602-2615,14.基金项目
国家自然科学基金项目(No.61602373) （No.61602373）
陕西省教育厅青年创新团队项目(No.24JP116) （No.24JP116）
中国国家留学基金资助 （）
