Signature descriptor for free form trajectory modeling

Shandong Wu; Youfu Li; Jianwei Zhang

doi:10.1109/ICITECHNOLOGY.2007.4290453

Signature descriptor for free form trajectory modeling

Shandong Wu
, Youfu Li
, Jianwei Zhang

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

6 Citations (Scopus)

Abstract

Motion trajectory modeling plays important role in characterizing human or robot action and behavior. However, effective and capable descriptors are lacking that can fully depict space trajectories. In this paper, we propose a novel signature mechanism for free form trajectory modeling in Euclidean space. The signature admits rich invariants due to the computational locality. By implementing the approximate signature, the noise-sensitive high order derivatives are avoided. The trajectory is recognized based on the customized signatures similarity metric. The conducted experiments verified the signature's effectiveness and robustness in 3-D trajectory representation and recognition. © 2007 IEEE.

Original language	English
Title of host publication	IEEE ICIT 2007 - 2007 IEEE International Conference on Integration Technology
Pages	167-172
DOIs	https://doi.org/10.1109/ICITECHNOLOGY.2007.4290453
Publication status	Published - 2007
Event	2007 IEEE International Conference on Integration Technology, ICIT 2007 - Shenzhen, China Duration: 20 Mar 2007 → 24 Mar 2007

Conference

Conference	2007 IEEE International Conference on Integration Technology, ICIT 2007
Place	China
City	Shenzhen
Period	20/03/07 → 24/03/07

Research Keywords

Approximate solution
Differential invariants
Robot vision
Signature descriptor
Trajectory modeling

Access Output

10.1109/ICITECHNOLOGY.2007.4290453

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{12f041b077c149b785acb30b33a4e9d8,

title = "Signature descriptor for free form trajectory modeling",

abstract = "Motion trajectory modeling plays important role in characterizing human or robot action and behavior. However, effective and capable descriptors are lacking that can fully depict space trajectories. In this paper, we propose a novel signature mechanism for free form trajectory modeling in Euclidean space. The signature admits rich invariants due to the computational locality. By implementing the approximate signature, the noise-sensitive high order derivatives are avoided. The trajectory is recognized based on the customized signatures similarity metric. The conducted experiments verified the signature's effectiveness and robustness in 3-D trajectory representation and recognition. {\textcopyright} 2007 IEEE.",

keywords = "Approximate solution, Differential invariants, Robot vision, Signature descriptor, Trajectory modeling",

author = "Shandong Wu and Youfu Li and Jianwei Zhang",

year = "2007",

doi = "10.1109/ICITECHNOLOGY.2007.4290453",

language = "English",

isbn = "1424410924",

pages = "167--172",

booktitle = "IEEE ICIT 2007 - 2007 IEEE International Conference on Integration Technology",

note = "2007 IEEE International Conference on Integration Technology, ICIT 2007 ; Conference date: 20-03-2007 Through 24-03-2007",

}

TY - GEN

T1 - Signature descriptor for free form trajectory modeling

AU - Wu, Shandong

AU - Li, Youfu

AU - Zhang, Jianwei

PY - 2007

Y1 - 2007

N2 - Motion trajectory modeling plays important role in characterizing human or robot action and behavior. However, effective and capable descriptors are lacking that can fully depict space trajectories. In this paper, we propose a novel signature mechanism for free form trajectory modeling in Euclidean space. The signature admits rich invariants due to the computational locality. By implementing the approximate signature, the noise-sensitive high order derivatives are avoided. The trajectory is recognized based on the customized signatures similarity metric. The conducted experiments verified the signature's effectiveness and robustness in 3-D trajectory representation and recognition. © 2007 IEEE.

AB - Motion trajectory modeling plays important role in characterizing human or robot action and behavior. However, effective and capable descriptors are lacking that can fully depict space trajectories. In this paper, we propose a novel signature mechanism for free form trajectory modeling in Euclidean space. The signature admits rich invariants due to the computational locality. By implementing the approximate signature, the noise-sensitive high order derivatives are avoided. The trajectory is recognized based on the customized signatures similarity metric. The conducted experiments verified the signature's effectiveness and robustness in 3-D trajectory representation and recognition. © 2007 IEEE.

KW - Approximate solution

KW - Differential invariants

KW - Robot vision

KW - Signature descriptor

KW - Trajectory modeling

UR - https://www.scopus.com/pages/publications/46449099877

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-46449099877&origin=recordpage

U2 - 10.1109/ICITECHNOLOGY.2007.4290453

DO - 10.1109/ICITECHNOLOGY.2007.4290453

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

SN - 1424410924

SN - 9781424410927

SP - 167

EP - 172

BT - IEEE ICIT 2007 - 2007 IEEE International Conference on Integration Technology

T2 - 2007 IEEE International Conference on Integration Technology, ICIT 2007

Y2 - 20 March 2007 through 24 March 2007

ER -

Signature descriptor for free form trajectory modeling

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this