OPT OpenIR  > 光谱成像技术研究室
Adaptive 3D shape context representation for motion trajectory classification
Liu, Weihua1; Li, Zuhe2; Zhang, Geng1; Zhang, Zhong3; Liu, WH (reprint author), Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol, Xian, Peoples R China.
作者部门光谱成像技术实验室
2017-07-01
发表期刊MULTIMEDIA TOOLS AND APPLICATIONS
ISSN1380-7501
卷号76期号:14页码:15413-15434
产权排序1
摘要

The measurement of similarity between two motion trajectories is one of the fundamental task for motion analysis, perception and recognition. Previous research focus on 2D trajectory similarity measurement. With the advent of 3D sensors, it is possible to collect large amounts of 3D trajectory data for more precise motion representation. As trajectories in 3D space may often exhibit a similar motion pattern but may differ in location, orientation, scale, and appearance variations, the trajectory descriptor must be invariant to these degrees of freedom. Shape context is one of the rich local shape descriptors can be used to represent the trajectory in 2D space, however, rarely applied in the 3D motion trajectory recognition field. To handle 3D data, in this paper, we first naturally extend the shape context into the spatiotemporal domain by adopting a spherical neighborhood, and named it 3D Shape Context(3DSC). To achieve better global invariant on trajectories classification, the adaptive outer radius of 3DSC for extracting 3D Shape Context feature is proposed. The advantages of our proposed 3D shape context are: (1) It is invariant to motion trajectories translation and scale in the spatiotemporal domain; (2) It contains the whole trajectory points in the 3DSC ball volume, thus can achieve global information representation and is good for solving sub-trajectories problem; (3) It is insensitive to the appearance variations in the identical meaning trajectories, meanwhile, can greatly discriminate the distinct meaning trajectories. In trajectory recognition phase, we consider a feature-to-feature alignment between motion trajectories based on dynamic time warping and then use the one nearest neighbor (1NN) classifier for final accuracy evaluation. We test the performance of proposed 3D SC-DTW on UCI ASL large dataset, Digital hand dataset and the experimental results demonstrate the effectiveness of our method.

文章类型Article
关键词Gesture Trajectory Shape Context Dynamic Time Warping Gesture Classification
学科领域Computer Science, Information Systems
WOS标题词Science & Technology ; Technology
DOI10.1007/s11042-016-3841-0
收录类别SCI ; EI
关键词[WOS]RECOGNITION ; RETRIEVAL ; GESTURES
语种英语
WOS研究方向Computer Science ; Engineering
项目资助者National Natural Science Foundation of China, "Light of West China" Program of Chinese Academy of Sciences(61501456)
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000404609900010
引用统计
被引频次:2[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.opt.ac.cn/handle/181661/29101
专题光谱成像技术研究室
通讯作者Liu, WH (reprint author), Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol, Xian, Peoples R China.
作者单位1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol, Xian, Peoples R China
2.Zhengzhou Univ Light Ind, Sch Comp & Commun Engn, Zhengzhou, Peoples R China
3.Univ Texas Arlington, Arlington, TX 76019 USA
推荐引用方式
GB/T 7714
Liu, Weihua,Li, Zuhe,Zhang, Geng,et al. Adaptive 3D shape context representation for motion trajectory classification[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2017,76(14):15413-15434.
APA Liu, Weihua,Li, Zuhe,Zhang, Geng,Zhang, Zhong,&Liu, WH .(2017).Adaptive 3D shape context representation for motion trajectory classification.MULTIMEDIA TOOLS AND APPLICATIONS,76(14),15413-15434.
MLA Liu, Weihua,et al."Adaptive 3D shape context representation for motion trajectory classification".MULTIMEDIA TOOLS AND APPLICATIONS 76.14(2017):15413-15434.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Adaptive 3D shape co(2329KB)期刊论文作者接受稿限制开放CC BY-NC-SA请求全文
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
[Liu, Weihua]的文章
[Li, Zuhe]的文章
[Zhang, Geng]的文章
百度学术
百度学术中相似的文章
[Liu, Weihua]的文章
[Li, Zuhe]的文章
[Zhang, Geng]的文章
必应学术
必应学术中相似的文章
[Liu, Weihua]的文章
[Li, Zuhe]的文章
[Zhang, Geng]的文章
相关权益政策
暂无数据
收藏/分享
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。