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

Chen-Chien James Hsu; Wei Chen Liu; Chin-Ming Hong

doi:10.1109/ICSSE.2011.5961876

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

Chen-Chien James Hsu, Wei Chen Liu, Chin-Ming Hong

Department of Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011
Pages	70-75
Number of pages	6
DOIs	https://doi.org/10.1109/ICSSE.2011.5961876
Publication status	Published - 2011 Aug 24
Event	2011 International Conference on System Science and Engineering, ICSSE 2011 - Macao, China Duration: 2011 Jun 8 → 2011 Jun 10

Publication series

Name	Proceedings 2011 International Conference on System Science and Engineering, ICSSE 2011

Other

Other	2011 International Conference on System Science and Engineering, ICSSE 2011
Country	China
City	Macao
Period	2011/06/08 → 2011/06/10

Keywords

computer vision
historical trajectories
motion detection
object trajectory
optical flow

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1109/ICSSE.2011.5961876

Fingerprint Dive into the research topics of 'Real-time recognition of moving direction of a target object based on historical trajectories'. Together they form a unique fingerprint.

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 proceeding › Conference 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, 2011/06/08. 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

@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 = aug,

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",

note = "2011 International Conference on System Science and Engineering, ICSSE 2011 ; Conference date: 08-06-2011 Through 10-06-2011",

}

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

T2 - 2011 International Conference on System Science and Engineering, ICSSE 2011

Y2 - 8 June 2011 through 10 June 2011

ER -