Real-time recognition of moving direction of a target object based on historical trajectories

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

Abstract

This paper presents an effective algorithm to identify moving direction of an object in images based on historical trajectories of the moving object. By continuously acquiring images, temporal differencing is performed to detect the moving object followed by median filtering to reduce noises in the images. After that, opening operation is adopted to remove small objects lacking momentum in the binary image and strengthen the surrounding thickness of those with sufficient momentum. Historical trajectories can therefore be constructed by decreasing the momentum of the binary images as time elapsed based on established rules to decide the moving direction of objects.

Original languageEnglish
Title of host publicationProceedings 2011 International Conference on System Science and Engineering, ICSSE 2011
Pages70-75
Number of pages6
DOIs
Publication statusPublished - 2011 Aug 24
Event2011 International Conference on System Science and Engineering, ICSSE 2011 - Macao, China
Duration: 2011 Jun 82011 Jun 10

Publication series

NameProceedings 2011 International Conference on System Science and Engineering, ICSSE 2011

Other

Other2011 International Conference on System Science and Engineering, ICSSE 2011
CountryChina
CityMacao
Period11/6/811/6/10

Fingerprint

Momentum
Binary images
Trajectories

Keywords

  • computer vision
  • historical trajectories
  • motion detection
  • object trajectory
  • optical flow

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Hsu, C-C. J., Liu, W. C., & Hong, C-M. (2011). Real-time recognition of moving direction of a target object based on historical trajectories. In Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011 (pp. 70-75). [5961876] (Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011). https://doi.org/10.1109/ICSSE.2011.5961876

Real-time recognition of moving direction of a target object based on historical trajectories. / Hsu, Chen-Chien James; Liu, Wei Chen; Hong, Chin-Ming.

Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011. 2011. p. 70-75 5961876 (Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011).

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

Hsu, C-CJ, Liu, WC & Hong, C-M 2011, Real-time recognition of moving direction of a target object based on historical trajectories. in Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011., 5961876, Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011, pp. 70-75, 2011 International Conference on System Science and Engineering, ICSSE 2011, Macao, China, 11/6/8. https://doi.org/10.1109/ICSSE.2011.5961876
Hsu C-CJ, Liu WC, Hong C-M. Real-time recognition of moving direction of a target object based on historical trajectories. In Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011. 2011. p. 70-75. 5961876. (Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011). https://doi.org/10.1109/ICSSE.2011.5961876
Hsu, Chen-Chien James ; Liu, Wei Chen ; Hong, Chin-Ming. / Real-time recognition of moving direction of a target object based on historical trajectories. Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011. 2011. pp. 70-75 (Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011).
@inproceedings{a4db26d37a6746c69c29e8a1ff3c56c9,
title = "Real-time recognition of moving direction of a target object based on historical trajectories",
abstract = "This paper presents an effective algorithm to identify moving direction of an object in images based on historical trajectories of the moving object. By continuously acquiring images, temporal differencing is performed to detect the moving object followed by median filtering to reduce noises in the images. After that, opening operation is adopted to remove small objects lacking momentum in the binary image and strengthen the surrounding thickness of those with sufficient momentum. Historical trajectories can therefore be constructed by decreasing the momentum of the binary images as time elapsed based on established rules to decide the moving direction of objects.",
keywords = "computer vision, historical trajectories, motion detection, object trajectory, optical flow",
author = "Hsu, {Chen-Chien James} and Liu, {Wei Chen} and Chin-Ming Hong",
year = "2011",
month = "8",
day = "24",
doi = "10.1109/ICSSE.2011.5961876",
language = "English",
isbn = "9781612844718",
series = "Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011",
pages = "70--75",
booktitle = "Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011",

}

TY - GEN

T1 - Real-time recognition of moving direction of a target object based on historical trajectories

AU - Hsu, Chen-Chien James

AU - Liu, Wei Chen

AU - Hong, Chin-Ming

PY - 2011/8/24

Y1 - 2011/8/24

N2 - This paper presents an effective algorithm to identify moving direction of an object in images based on historical trajectories of the moving object. By continuously acquiring images, temporal differencing is performed to detect the moving object followed by median filtering to reduce noises in the images. After that, opening operation is adopted to remove small objects lacking momentum in the binary image and strengthen the surrounding thickness of those with sufficient momentum. Historical trajectories can therefore be constructed by decreasing the momentum of the binary images as time elapsed based on established rules to decide the moving direction of objects.

AB - This paper presents an effective algorithm to identify moving direction of an object in images based on historical trajectories of the moving object. By continuously acquiring images, temporal differencing is performed to detect the moving object followed by median filtering to reduce noises in the images. After that, opening operation is adopted to remove small objects lacking momentum in the binary image and strengthen the surrounding thickness of those with sufficient momentum. Historical trajectories can therefore be constructed by decreasing the momentum of the binary images as time elapsed based on established rules to decide the moving direction of objects.

KW - computer vision

KW - historical trajectories

KW - motion detection

KW - object trajectory

KW - optical flow

UR - http://www.scopus.com/inward/record.url?scp=84860397081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860397081&partnerID=8YFLogxK

U2 - 10.1109/ICSSE.2011.5961876

DO - 10.1109/ICSSE.2011.5961876

M3 - Conference contribution

AN - SCOPUS:84860397081

SN - 9781612844718

T3 - Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011

SP - 70

EP - 75

BT - Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011

ER -