基于神经网络的3D点云模型识别的方法  

Method of 3D Point Cloud Model Recognition Based on Neural Network

作　　者：吴鹏程 李晖[1] 王凤聪 WU Pengcheng;LI Hui;WANG Fengcong(Shenyang University of Technology,Shenyang 110870,China)

机构地区：[1]沈阳工业大学,辽宁沈阳110870

出　　处：《现代信息科技》2023年第7期93-97,共5页Modern Information Technology

摘　　要：针对点云的三维模型识别方法缺乏局部空间特征,从而影响3D模型的类识别的问题,提出一种基于残差模块的卷积神经网络三维模型识别方法。通过引入残差模块,构建深层神经网络增强点云模型的局部信息,提高物体的识别精度。同时,采用了一种获取多尺度局部空间信息的策略,加快了模型的推理能力。实验证明,算法识别准确率达到了91.5%,加快了模型的推理速度,可应用于对点云模型识别有实时性要求的场景,如:流水线上物体的检测等。Aiming at the problem that the 3D model recognition method of point cloud lacks local spatial features,which affects the class recognition of 3D model,a convolution neural network 3D model recognition method based on residual module is proposed.By introducing the residual module,a deep neural network is constructed to enhance the local information of the point cloud model and improve the object recognition accuracy.At the same time,a strategy of acquiring multi-scale local spatial information is adopted to accelerate the reasoning ability of the model.The experimental results prove that the recognition accuracy of the algorithm reaches 91.5%,which speeds up the reasoning speed of the model.And it can be applied to scenes that require real-time point cloud model recognition,such as object detection on the pipeline.

关 键 词：三维模型识别 卷积神经网络 实时性 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]