基于卷积神经网络和NBV的三维重建方法  

3D reconstruction method based on convolution neural network&NBV

作　　者：李爱军 Li Aijun(School of Electronic Information Engineering,Tianjin Vocational University,Tianjin 300410,China)

机构地区：[1]天津职业大学电子信息工程学院,天津300410

出　　处：《电子测量技术》2021年第8期70-75,共6页Electronic Measurement Technology

基　　金：天津市教育科学“十三五”规划课题(VESP3011);2018年全国高等院校计算机基础教育研究会教学改革重点项目(2018-AFCEC-035);2021年全国高等院校计算机基础教育研究会教学改革项目(2021-AFCEC-429)资助。

摘　　要：为了使三维(3D)重建适用于多种目标形状,并提高处理速度,提出一种基于机器学习的3D重建方法,重点解决“下一个最优视点”(NBV)规划问题。首先,给出NBV的定义和计算,建立离散NBV搜索空间;然后,生成NBV,同时对该空间进行迭代式重建。此外,为了处理NBV的学习问题,提出一个基于3D卷积神经网络的分类方法,将可能的传感器位姿考虑为一个分类问题。实验结果表明,所提方法的重建精度优于VoxNet网络方法,能较好地满足约束条件;与高精度信息增益方法相比,所提方法也取得了较优和接近的重建覆盖率,对于不同形状,基本上4次扫描就可以达到较高的覆盖率,且重建速度快约90倍。To make 3D reconstruction suitable for various target shapes and improve the processing speed,a 3D reconstruction method based on machine learning is proposed,which focuses on solving the"next best viewpoint"(NBV)planning problem.Firstly,the definition and calculation of NBV are given,and the discrete NBV search space is established.Then,NBV is generated,and the space is reconstructed iteratively.In addition,in order to deal with the learning problem of NBV,a classification method based on 3D convolution neural network is proposed,which considers the possible position and pose of sensor as a classification problem.The experimental results show that the reconstruction accuracy of the proposed method is better than that of the VoxNet network method,which can meet the constraints better.Compared with the high-precision information gain method,the proposed method also achieves better and close reconstruction coverage.Basically,it can achieve high coverage in 4 scans for different shapes,and the reconstruction speed is about 90 times faster.

关 键 词：三维重建 下一个最优视点 分类问题 卷积神经网络 处理速度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]