Trajectory kinematics descriptor for trajectory clustering in surveillance videos

Wei Cheng Wang, Pau-Choo Chung, Hsin Wei Cheng, Chun Rong Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Trajectories provide spatial-temporal information of foreground objects for event clustering and analysis. Because of the kinematic properties of foreground objects, the lengths of trajectories will be different which lead to the length problem of assessing similarity between two or more trajectories. To solve the problem, we propose a novel descriptor named trajectory kinematics descriptor to represent trajectories based on the kinematic properties from the point-of-view of Frenet-Serret frames. As shown in the experiments, applying the proposed trajectory kinematics descriptor for event clustering can achieve better F-measure scores compared to the state-of-the-art methods.

Original languageEnglish
Title of host publication2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1198-1201
Number of pages4
ISBN (Electronic)9781479983919
DOIs
Publication statusPublished - 2015 Jul 27
EventIEEE International Symposium on Circuits and Systems, ISCAS 2015 - Lisbon, Portugal
Duration: 2015 May 242015 May 27

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2015-July
ISSN (Print)0271-4310

Other

OtherIEEE International Symposium on Circuits and Systems, ISCAS 2015
CountryPortugal
CityLisbon
Period15-05-2415-05-27

Fingerprint

Kinematics
Trajectories
Experiments

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Wang, W. C., Chung, P-C., Cheng, H. W., & Huang, C. R. (2015). Trajectory kinematics descriptor for trajectory clustering in surveillance videos. In 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015 (pp. 1198-1201). [7168854] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2015-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2015.7168854
Wang, Wei Cheng ; Chung, Pau-Choo ; Cheng, Hsin Wei ; Huang, Chun Rong. / Trajectory kinematics descriptor for trajectory clustering in surveillance videos. 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1198-1201 (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{1bbc8049d27f4e3f951b5be71dbf1a70,
title = "Trajectory kinematics descriptor for trajectory clustering in surveillance videos",
abstract = "Trajectories provide spatial-temporal information of foreground objects for event clustering and analysis. Because of the kinematic properties of foreground objects, the lengths of trajectories will be different which lead to the length problem of assessing similarity between two or more trajectories. To solve the problem, we propose a novel descriptor named trajectory kinematics descriptor to represent trajectories based on the kinematic properties from the point-of-view of Frenet-Serret frames. As shown in the experiments, applying the proposed trajectory kinematics descriptor for event clustering can achieve better F-measure scores compared to the state-of-the-art methods.",
author = "Wang, {Wei Cheng} and Pau-Choo Chung and Cheng, {Hsin Wei} and Huang, {Chun Rong}",
year = "2015",
month = "7",
day = "27",
doi = "10.1109/ISCAS.2015.7168854",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1198--1201",
booktitle = "2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015",
address = "United States",

}

Wang, WC, Chung, P-C, Cheng, HW & Huang, CR 2015, Trajectory kinematics descriptor for trajectory clustering in surveillance videos. in 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015., 7168854, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2015-July, Institute of Electrical and Electronics Engineers Inc., pp. 1198-1201, IEEE International Symposium on Circuits and Systems, ISCAS 2015, Lisbon, Portugal, 15-05-24. https://doi.org/10.1109/ISCAS.2015.7168854

Trajectory kinematics descriptor for trajectory clustering in surveillance videos. / Wang, Wei Cheng; Chung, Pau-Choo; Cheng, Hsin Wei; Huang, Chun Rong.

2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1198-1201 7168854 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2015-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Trajectory kinematics descriptor for trajectory clustering in surveillance videos

AU - Wang, Wei Cheng

AU - Chung, Pau-Choo

AU - Cheng, Hsin Wei

AU - Huang, Chun Rong

PY - 2015/7/27

Y1 - 2015/7/27

N2 - Trajectories provide spatial-temporal information of foreground objects for event clustering and analysis. Because of the kinematic properties of foreground objects, the lengths of trajectories will be different which lead to the length problem of assessing similarity between two or more trajectories. To solve the problem, we propose a novel descriptor named trajectory kinematics descriptor to represent trajectories based on the kinematic properties from the point-of-view of Frenet-Serret frames. As shown in the experiments, applying the proposed trajectory kinematics descriptor for event clustering can achieve better F-measure scores compared to the state-of-the-art methods.

AB - Trajectories provide spatial-temporal information of foreground objects for event clustering and analysis. Because of the kinematic properties of foreground objects, the lengths of trajectories will be different which lead to the length problem of assessing similarity between two or more trajectories. To solve the problem, we propose a novel descriptor named trajectory kinematics descriptor to represent trajectories based on the kinematic properties from the point-of-view of Frenet-Serret frames. As shown in the experiments, applying the proposed trajectory kinematics descriptor for event clustering can achieve better F-measure scores compared to the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84946212552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946212552&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2015.7168854

DO - 10.1109/ISCAS.2015.7168854

M3 - Conference contribution

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 1198

EP - 1201

BT - 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wang WC, Chung P-C, Cheng HW, Huang CR. Trajectory kinematics descriptor for trajectory clustering in surveillance videos. In 2015 IEEE International Symposium on Circuits and Systems, ISCAS 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1198-1201. 7168854. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.2015.7168854