摘要
针对复杂结构的三维形状分析与识别问题,提出了新颖的图卷积分类方法,建立了局部几何与全局结构联合图卷积学习机制,有效提高了三维形状数据学习的鲁棒性与稳定性。首先,通过最远点采样与最近邻方法构造局部图,并建立动态卷积算子,有效提取局部几何特征;同时,基于特征域采样构造全局的特征谱图,通过卷积算子获得全局结构信息。进而,构建加权的联合图卷积学习网络模型,引入注意力机制,实现自适应的特征融合。最终,在联合优化目标函数约束下,有效提高特征学习的性能。实验结果表明,融合局部几何与全局结构的联合图卷积网络学习机制,有效提高了深度特征的表示能力及区分性,具有更优秀的识别力和分类性能。该研究方法可应用于大规模三维场景识别、三维重建以及数据压缩,在机器人、产品数字化分析、智能导航、虚拟现实等领域具有着重要的工程意义与广泛的应用前景。
Aiming at the issue of complex 3D shape analysis and recognition,this paper presented a novel 3D graph convolution classification method.It established a joint graph convolution learning mechanism of local geometry and global structure to provide both geometrical features and global context features,which effectively improved the robustness and stability of 3D data learning.Firstly,it constructed the local graph in spatial domain by farthest point sampling and K-nearest neighbor method,and designed a dynamic spectral graph convolution operator to extract local geometric features effectively.Meanwhile,it constructed the global feature graph based on random sampling in the feature domain,and obtained the global structure context by spectral graph convolution.Furthermore,it established a weighted graph convolution network with an attention mechanism to achieve adaptive feature fusion.Finally,under the optimization of objective function,it improved the performance of feature learning effectively.Experimental results show that the proposed joint network learning mechanism,which combined local geometric features with global structure features,enhances the representation ability and discrimination of deep features,and obtains better recognition and classification performance compared with advanced methods.This method can be used for large-scale point clouds recognition,3D shape reconstruction and data compression.It has important research significance and broad application prospects in robot,product digital analysis,intelligent navigation,virtual reality and other fields.
作者
张晓辉
何金海
兰鹏燕
徐圣斯
Zhang Xiaohui;He Jinhai;Lan Pengyan;Xu Shengsi(School of Computer Science&Information Technology,Liaoning Normal University,Dalian Liaoning 116081,China;Information Technology Center,Dalian Polytechnic University,Dalian Liaoning 116034,China)
出处
《计算机应用研究》
CSCD
北大核心
2023年第12期3828-3833,共6页
Application Research of Computers
基金
辽宁省科技厅资助项目(2023JH2/101300190)
辽宁省教育厅一般项目(LJ2020015)。
关键词
深度学习
形状分类
三维形状
图卷积
局部几何
全局结构
deep learning
shape classification
three-dimensional shape
graph convolution
local geometry
global structure
