RGB-D-based Human Motion Recognition with Deep Learning: A Survey
Pichao Wang2; Wanqing Li2; Philip Ogunbona2; Jun Wan1; Sergio Escalera
2018
发表期刊Computer Vision and Image Understanding
卷号PP期号:1页码:1-22
摘要Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention. Along with the development in artificial intelligence, deep learning techniques have gained remarkable success in computer vision. In particular, convolutional neural networks (CNN) have achieved great success for image-based tasks, and recurrent neural networks (RNN) are renowned for sequence-based problems. Specifically, deep learning methods based on the CNN and RNN architectures have been adopted for motion recognition using RGB-D data. In this paper, a detailed overview of recent advances in RGB-D-based motion recognition is presented. The reviewed methods are broadly categorized into four groups, depending on the modality adopted for recognition: RGBbased, depth-based, skeleton-based and RGB+D-based. As a survey focused on the application of deep learning to RGB-D-based motion recognition, we explicitly discuss the advantages and limitations of existing techniques. Particularly, we highlighted the methods of encoding spatial-temporal-structural information inherent in video sequence, and discuss potential directions for future research.
关键词Human Motion Recognition Rgb-d Data Deep Learning Survey
收录类别SCI
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21705
专题模式识别国家重点实验室_生物识别与安全技术研究
作者单位1.Center for Biometrics and Security Research & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.University of Wollongong, Australia
3.c University of Barcelona and Computer Vision Center, Spain
推荐引用方式
GB/T 7714
Pichao Wang,Wanqing Li,Philip Ogunbona,et al. RGB-D-based Human Motion Recognition with Deep Learning: A Survey[J]. Computer Vision and Image Understanding,2018,PP(1):1-22.
APA Pichao Wang,Wanqing Li,Philip Ogunbona,Jun Wan,&Sergio Escalera.(2018).RGB-D-based Human Motion Recognition with Deep Learning: A Survey.Computer Vision and Image Understanding,PP(1),1-22.
MLA Pichao Wang,et al."RGB-D-based Human Motion Recognition with Deep Learning: A Survey".Computer Vision and Image Understanding PP.1(2018):1-22.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
CVIU2018_survery.pdf(5390KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Pichao Wang]的文章
[Wanqing Li]的文章
[Philip Ogunbona]的文章
百度学术
百度学术中相似的文章
[Pichao Wang]的文章
[Wanqing Li]的文章
[Philip Ogunbona]的文章
必应学术
必应学术中相似的文章
[Pichao Wang]的文章
[Wanqing Li]的文章
[Philip Ogunbona]的文章
相关权益政策
暂无数据
收藏/分享
文件名: CVIU2018_survery.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。