Invariant trajectory indexing for real time 3D motion recognition

Jianyu Yang; Y. F. Li; Keyi Wang

doi:10.1109/IROS.2011.6048210

Invariant trajectory indexing for real time 3D motion recognition

Jianyu Yang
, Y. F. Li
, Keyi Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

12 Citations (Scopus)

Abstract

Motion trajectory description plays an important role in motion recognition for many robotic tasks. The previous methods are too high in computational cost for real time recognition. In this paper, we propose a novel indexing method for motion trajectories as a high level invariant descriptor. Trajectories are segmented into basic segments and represented in segment level rather than point level. We index the trajectories by their segment sequences to recognize them. The computational cost is significantly decreased and the experimental results show that this method is effective and it can be used for real time motion recognition. The accuracy is also preserved for long term trajectories. © 2011 IEEE.

Original language	English
Title of host publication	IEEE International Conference on Intelligent Robots and Systems
Pages	3440-3445
DOIs	https://doi.org/10.1109/IROS.2011.6048210
Publication status	Published - 2011
Event	2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '11): Celebrating 50 Years of Robotics - San Francisco, United States Duration: 25 Sept 2011 → 30 Sept 2011 https://ieeexplore.ieee.org/xpl/conhome/6034548/proceeding

Conference

Conference	2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '11)
Place	United States
City	San Francisco
Period	25/09/11 → 30/09/11
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6034548/proceeding

Access Output

10.1109/IROS.2011.6048210

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{ed8a4fe8e8f1468bba0b471b5a57ff9f,

title = "Invariant trajectory indexing for real time 3D motion recognition",

abstract = "Motion trajectory description plays an important role in motion recognition for many robotic tasks. The previous methods are too high in computational cost for real time recognition. In this paper, we propose a novel indexing method for motion trajectories as a high level invariant descriptor. Trajectories are segmented into basic segments and represented in segment level rather than point level. We index the trajectories by their segment sequences to recognize them. The computational cost is significantly decreased and the experimental results show that this method is effective and it can be used for real time motion recognition. The accuracy is also preserved for long term trajectories. {\textcopyright} 2011 IEEE.",

author = "Jianyu Yang and Li, \{Y. F.\} and Keyi Wang",

year = "2011",

doi = "10.1109/IROS.2011.6048210",

language = "English",

isbn = "9781612844541",

pages = "3440--3445",

booktitle = "IEEE International Conference on Intelligent Robots and Systems",

note = "2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '11) : Celebrating 50 Years of Robotics ; Conference date: 25-09-2011 Through 30-09-2011",

url = "https://ieeexplore.ieee.org/xpl/conhome/6034548/proceeding",

}

Yang, J, Li, YF & Wang, K 2011, Invariant trajectory indexing for real time 3D motion recognition. in IEEE International Conference on Intelligent Robots and Systems., 6048210, pp. 3440-3445, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '11), San Francisco, California, United States, 25/09/11. https://doi.org/10.1109/IROS.2011.6048210

TY - GEN

T1 - Invariant trajectory indexing for real time 3D motion recognition

AU - Yang, Jianyu

AU - Li, Y. F.

AU - Wang, Keyi

PY - 2011

Y1 - 2011

N2 - Motion trajectory description plays an important role in motion recognition for many robotic tasks. The previous methods are too high in computational cost for real time recognition. In this paper, we propose a novel indexing method for motion trajectories as a high level invariant descriptor. Trajectories are segmented into basic segments and represented in segment level rather than point level. We index the trajectories by their segment sequences to recognize them. The computational cost is significantly decreased and the experimental results show that this method is effective and it can be used for real time motion recognition. The accuracy is also preserved for long term trajectories. © 2011 IEEE.

AB - Motion trajectory description plays an important role in motion recognition for many robotic tasks. The previous methods are too high in computational cost for real time recognition. In this paper, we propose a novel indexing method for motion trajectories as a high level invariant descriptor. Trajectories are segmented into basic segments and represented in segment level rather than point level. We index the trajectories by their segment sequences to recognize them. The computational cost is significantly decreased and the experimental results show that this method is effective and it can be used for real time motion recognition. The accuracy is also preserved for long term trajectories. © 2011 IEEE.

UR - https://www.scopus.com/pages/publications/84455206657

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84455206657&origin=recordpage

U2 - 10.1109/IROS.2011.6048210

DO - 10.1109/IROS.2011.6048210

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781612844541

SP - 3440

EP - 3445

BT - IEEE International Conference on Intelligent Robots and Systems

T2 - 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS '11)

Y2 - 25 September 2011 through 30 September 2011

ER -

Invariant trajectory indexing for real time 3D motion recognition

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this