摘要
现阶段点云分类研究已被广泛应用于机器人操作、自主驾驶和虚拟现实等多个领域,提取既丰富又具有高判别能力的特征是3D点云分类的关键.为此,文中设计基于局部-非局部交互卷积的3D点云分类算法,改善点云的特征提取.首先,构造局部-非局部交互卷积模块,在获取局部相似特征和非局部相似特征的基础上,采用交互增强,缓解单个邻域在表示封闭区域时存在的冗余问题,增强网络的层次性和稳定性,同时也缓解网络的退化问题.然后,以该模块为基本单元构建卷积神经网络.最后,采用自适应特征融合,充分利用不同层次的特征,实现3D点云的分类.在ModelNet40、ScanObjectNN基准数据集上的实验表明,文中算法性能较优.
Now 3D point cloud classificaiton is widely applied in many domains,including robot operation,automous driving and virtual reality.Extracting rich features with high discrimination is the key to 3D point cloud classification.Therefore,an algorithm of 3D point cloud classification based on local-nonlocal interactive convolution is designed to improve the feature extraction of point cloud.Firstly,a local-nonlocal interactive convolution module is constructed.After obtaining local and nonlocal similar features,interactive enhancement is employed to alleviate the redundancy problem caused by a single neighborhood representing a closed region.Consequently,the hierarchy and stability of the network are enhanced and the degradation problem of the network is alleviated.Then,the convolution neural network is constructed with the module as the basic unit.Finally,adaptive feature fusion is adopted to make full use of different levels of features to realize 3D point cloud classification.Experimental results on two benchmark datasets,ModelNet40 and ScanObjectNN,show that the proposed method generates better performance.
作者
芦新宇
杨冰
叶海良
曹飞龙
LU Xinyu;YANG Bing;YE Hailiang;CAO Feilong(Department of Applied Mathematics,College of Sciences,China Jiliang University,Hangzhou 310018)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2022年第2期141-149,共9页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.62032022,62006215)资助。
关键词
深度学习
点云分类
局部-非局部交互卷积
自适应特征融合
Deep Learning
Point Cloud Classification
Local-Nonlocal Interactive Convolution
Adaptive Feature Fusion
