机器学习在基于点云的三维物体识别领域的研究综述  

A Survey on Machine Learning in Recognition of 3D Object Based on Point Cloud

作　　者：解则晓[1] 李美慧 XIE Ze-Xiao;LI Mei-Hui(College of Engineering, Ocean University of China, Qingdao 266100, China)

机构地区：[1]中国海洋大学工程学院,山东青岛266100

出　　处：《中国海洋大学学报（自然科学版）》2021年第6期125-130,98,共7页Periodical of Ocean University of China

基　　金：国家自然科学基金项目(6197010781)资助。

摘　　要：随着机器学习算法的不断更新发展,加之其良好的适应性、准确性及鲁棒性,在三维物体识别领域获得了广泛的应用,成为当前点云处理的研究热点。首先,本文对三维物体点云数据识别及机器学习的发展应用进行归纳。然后,从特征选择、特征提取、特征识别三个方面,进行分析总结。最后,指出机器学习在基于点云的三维物体识别领域的应用目前所面临的挑战及进一步研究的方向。With the continuous development of machine learning algorithms,and its good adaptability,accuracy and robustness,it has been widely used in the field of 3D object recognition,and has become a research hotspot of current point cloud processing.Firstly,the development and application of point cloud data recognition for 3D objects and machine learning are summarized.Then,it is analyzed and summarized from the three aspects of feature selection,feature extraction and object recognition.Finally,the paper points out the challenges and further research directions of machine learning in the field of point cloud processing based on 3D object recognition.

关 键 词：机器学习 三维物体识别 点云 特征选择 特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]