[1]顾军华,李 炜,董永峰.基于点云数据的分割方法综述[J].燕山大学学报,2020,44(2):125-137.
 GU Junhua,LI Wei,DONG Yongfeng.Segmentation methods for point cloud: a survey[J].Journal of YanShan University,2020,44(2):125-137.
点击复制

基于点云数据的分割方法综述
分享到:

《燕山大学学报》[ISSN:1007-791X/CN:13-1219/N]

卷:
44
期数:
2020年第2期
页码:
125-137
栏目:
信息与计算机技术
出版日期:
2020-03-31

文章信息/Info

Title:
Segmentation methods for point cloud: a survey
文章编号:
1007-791X(2020)02-0125-13
作者:
顾军华1*李 炜2董永峰1
1. 河北工业大学 人工智能与数据科学学院,天津 300401;
2. 河北工业大学 电气工程学院,天津 300401
Author(s):
GU Junhua1 LI Wei2 DONG Yongfeng1
1. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China;
2. School of Electrical Engineering, Hebei University of Technology, Tianjin 300401, China
关键词:
深度学习点云语义分割实例分割
Keywords:
deep learning point cloud semantic segmentation instance segmentation
分类号:
TP181
文献标志码:
A
摘要:
点云是一种能够完整表达场景信息的重要数据格式。近年来,对于点云的探索引起了越来越多研究人员的关注,并且迅速在计算机视觉、自动驾驶和机器人等许多领域得到了广泛应用。但是,由于点云独特的数据形式,使用深度神经网络处理点云时面临着独特挑战,因此基于点云的深度学习方法仍处于起步阶段。最近,利用点云处理分割任务出现了许多优秀的方法。为了激发未来对点云研究的深入发展,本文对点云深度学习方法的最新进展进行回顾,涵盖了三个主要任务,包括点云语义分割、点云实例分割以及常用的三维图像数据集,对其中处理点云的深度学习经典方法展开对比分析,提供多种方法在不同数据集上的比较结果,并且提出了一些观点和未来研究方向。
Abstract:
Point cloud is an important data that represents complete information of the scene. Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. However, due to the unique characteristic, deep learning on point clouds is still in its infancy. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research,a comprehensive overview of recent progress in deep learning methods for point clouds segmentation tasks is provided in this paper. Three major tasks are stated,including point clouds semantic segmentation, point cloud instance segmentation and 3D image databases. It is also presented comparative results on several publicly available datasets and analyze the classic deep learningbased methods, together with insightful observations and inspiring future research directions.

相似文献/References:

[1]孔令富,杨大志,张世辉.基于并联机构的三维视觉重构系统点云自动配准[J].燕山大学学报,2008,(2):106.
 KONG Ling-fu,YANG Da-zhi,ZHANG Shi-hui.Automatic registration of point clouds based on 3D vision reconstruction system of parallel robot[J].Journal of YanShan University,2008,(2):106.
[2]胡正平,陈俊岭,王蒙,等.卷积神经网络分类模型在模式识别中的新进展[J].燕山大学学报,2015,(4):283.[doi:10.3969/j.issn.1007-791X.2015.04.001]
 HU Zheng-ping,CHEN Jun-ling,WANG Meng,et al.Recent progress on convolutional neural network in pattern recognition[J].Journal of YanShan University,2015,(2):283.[doi:10.3969/j.issn.1007-791X.2015.04.001]
[3]胡正平,何 薇,王 蒙,等.深度子空间联合稀疏表示单样本人脸识别算法[J].燕山大学学报,2018,42(5):409.[doi:10.3969/j.issn.1007-791X.2018.05.005]
 HU Zhengping,HE Wei,WANG Meng,et al.Deep subspace joined sparse representation for single sample face recognition[J].Journal of YanShan University,2018,42(2):409.[doi:10.3969/j.issn.1007-791X.2018.05.005]
[4]胡正平,张乐,李淑芳,等.视频监控系统异常目标检测与定位综述[J].燕山大学学报,2019,43(1):001.[doi:10.3969/j.issn.1007-791X.2019.01.001]
 HU Zhengping,ZHANG Le,LI Shufang,et al.Review of abnormal behavior detection and location for intelligent video surveillance systems[J].Journal of YanShan University,2019,43(2):001.[doi:10.3969/j.issn.1007-791X.2019.01.001]
[5]李均利,尹宽,储诚曦,等.视频目标跟踪技术综述研究[J].燕山大学学报,2019,43(3):251.[doi:10.3969/j.issn.1007-791X.2019.03.009]
 LI Junli,YIN Kuan,CHU Chengxi,et al.Review of video target tracking technology[J].Journal of YanShan University,2019,43(2):251.[doi:10.3969/j.issn.1007-791X.2019.03.009]
[6]胡正平,张敏姣,李淑芳,等.智能视频监控系统中行人再识别技术研究综述[J].燕山大学学报,2019,43(4):000.
[7]胡正平,张敏姣,李淑芳,等.智能视频监控系统中行人再识别技术研究综述[J].燕山大学学报,2019,43(5):377.[doi:10.3969/j.issn.1007791X.2019.05.001]
 HU Zhengping,ZHANG Minjiao,LI Shufang,et al.Review of person reidentification technology in intelligent video surveillance system[J].Journal of YanShan University,2019,43(2):377.[doi:10.3969/j.issn.1007791X.2019.05.001]

备注/Memo

备注/Memo:
收稿日期:2019-10-17        责任编辑:孙峰
基金项目:国家自然科学基金资助项目(41804118)
作者简介:*顾军华(1966-),男,河北赵县人,博士,教授,博士生导师,主要研究方向为数据挖掘、智能信息处理、信息采集与集成、智能计算与优化、功能与信息展示以及软件工程项目管理,Email:jhgu@hebut.edu.cn
更新日期/Last Update: 2020-04-22