Motion detection techniques using optical flow

A. A. Shafie, Fadhlan Hafiz, M. H. Ali

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Motion detection is very important in image processing. One way of detecting motion is using optical flow. Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. The method used for finding the optical flow in this project is assuming that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. This technique is later used in developing software for motion detection which has the capability to carry out four types of motion detection. The motion detection software presented in this project also can highlight motion region, count motion level as well as counting object numbers. Many objects such as vehicles and human from video streams can be recognized by applying optical flow technique.

Original languageEnglish
Pages (from-to)559-561
Number of pages3
JournalWorld Academy of Science, Engineering and Technology
Volume56
Publication statusPublished - Aug 2009
Externally publishedYes

Fingerprint

Optical flows
Flow velocity
Luminance
Image processing

Keywords

  • Background modeling
  • Motion detection
  • Motion trajectories
  • Optical flow
  • Velocity smoothness constant

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Motion detection techniques using optical flow. / Shafie, A. A.; Hafiz, Fadhlan; Ali, M. H.

In: World Academy of Science, Engineering and Technology, Vol. 56, 08.2009, p. 559-561.

Research output: Contribution to journalArticle

@article{52c3d2ca4dca40ebbd10697aa4dcb0b6,
title = "Motion detection techniques using optical flow",
abstract = "Motion detection is very important in image processing. One way of detecting motion is using optical flow. Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. The method used for finding the optical flow in this project is assuming that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. This technique is later used in developing software for motion detection which has the capability to carry out four types of motion detection. The motion detection software presented in this project also can highlight motion region, count motion level as well as counting object numbers. Many objects such as vehicles and human from video streams can be recognized by applying optical flow technique.",
keywords = "Background modeling, Motion detection, Motion trajectories, Optical flow, Velocity smoothness constant",
author = "Shafie, {A. A.} and Fadhlan Hafiz and Ali, {M. H.}",
year = "2009",
month = "8",
language = "English",
volume = "56",
pages = "559--561",
journal = "World Academy of Science, Engineering and Technology",
issn = "2010-376X",
publisher = "World Academy of Science Engineering and Technology",

}

TY - JOUR

T1 - Motion detection techniques using optical flow

AU - Shafie, A. A.

AU - Hafiz, Fadhlan

AU - Ali, M. H.

PY - 2009/8

Y1 - 2009/8

N2 - Motion detection is very important in image processing. One way of detecting motion is using optical flow. Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. The method used for finding the optical flow in this project is assuming that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. This technique is later used in developing software for motion detection which has the capability to carry out four types of motion detection. The motion detection software presented in this project also can highlight motion region, count motion level as well as counting object numbers. Many objects such as vehicles and human from video streams can be recognized by applying optical flow technique.

AB - Motion detection is very important in image processing. One way of detecting motion is using optical flow. Optical flow cannot be computed locally, since only one independent measurement is available from the image sequence at a point, while the flow velocity has two components. A second constraint is needed. The method used for finding the optical flow in this project is assuming that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image. This technique is later used in developing software for motion detection which has the capability to carry out four types of motion detection. The motion detection software presented in this project also can highlight motion region, count motion level as well as counting object numbers. Many objects such as vehicles and human from video streams can be recognized by applying optical flow technique.

KW - Background modeling

KW - Motion detection

KW - Motion trajectories

KW - Optical flow

KW - Velocity smoothness constant

UR - http://www.scopus.com/inward/record.url?scp=78651571073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651571073&partnerID=8YFLogxK

M3 - Article

VL - 56

SP - 559

EP - 561

JO - World Academy of Science, Engineering and Technology

JF - World Academy of Science, Engineering and Technology

SN - 2010-376X

ER -