An Automated Real-Time People Tracking System Based on KLT Features Detection

N. A.

doi:10.34028/iajit

Article Details

An Automated Real-Time People Tracking System Based on KLT Features Detection

Authors:

N. A.

Publisher:

Zarqa University, Jordan

Journal:

The International Arab Journal of Information Technology (IAJIT) Vol.9 Issue 1, pp.100-107

Document Type:

Article

Publication Date:

1/2012

Document Language:

English

Document ID (Org No.):

2001388812

pISSN:

2309-4524

DOI:

10.34028/iajit

Keywords:

Abstract:

 The  advancement  of  technology  allows  video  acquisit ion  devices  to  have  a  better  performance,  thereby  increasing 
the  number  of  applications  that  can  effectively  uti lize  digital  video.  Compared  to  still  images,  video   sequences  provide  more 
information  about  how  objects  and  scenarios  change  over  time.  Tracking  humans  is  of  interest  for  a  variety  of  applications 
including surveillance, activity monitoring and gat e analysis. Many efficient object tracking algorithms have been proposed in 
literature,  however  part  of  those  algorithms  are  se mi-automatic  requiring  human  interference.  As  for  t he  fully  automated 
algorithms, most of them are not applicable to real-time applications. This paper presents a low cost automatic object tracking 
algorithm  suitable  for  use  in  real-time  video  based   systems.  The  novelty  of  the  proposed  system  is  tha t  it  uses  a  simplified 
version  of  the  Kanade-Lucas-Tomasi  (KLT)  technique  to  detect  features  of  both  continuous  and  discontinuous  nature.  As 
discontinuous feature selection is subject to noise , and would result in non-optimal feature based obj ect tracking, the authors 
propose the  use of  a  Kalman filter  for  the purpose  of  seeking optimal  estimates  in tracking.  The  integrated tracking  system  is 
capable  of  handling  shadows  and  is  based  on  a  dynam ic  background  subtraction  strategy  that  minimises  errors  and  quickly 
adapts  to  scene  changes.  Experimental  results  are  p rovided  to  demonstrate  the  system’s  capability  of  accurately  tracking 
objects  in  real-time  applications  where  scenes  are  subject  to  noise  particularly  resulting  from  occlusions  and  sudden 
illumination variations.

Article Details

An Automated Real-Time People Tracking System Based on KLT Features Detection

Authors:

N. A.

Publisher:

Zarqa University, Jordan

Journal:

The International Arab Journal of Information Technology (IAJIT) Vol.9 Issue 1, pp.100-107

Document Type:

Article

Publication Date:

1/2012

Document Language:

English

Document ID (Org No.):

2001388812

pISSN:

2309-4524

DOI:

10.34028/iajit

Object tracking

kalman-filter

features selection

KLT

Issues

Article Details

An Automated Real-Time People Tracking System Based on KLT Features Detection

Authors: N. A.

Publisher: Zarqa University, Jordan

Journal: The International Arab Journal of Information Technology (IAJIT) Vol.9 Issue 1, pp.100-107

Document Type: Article

Publication Date: 1/2012

Document Language: English

Document ID (Org No.): 2001388812

pISSN: 2309-4524

DOI: 10.34028/iajit

Object tracking

kalman-filter

features selection

KLT

Issues

Authors:

N. A.

Publisher:

Zarqa University, Jordan

Journal:

The International Arab Journal of Information Technology (IAJIT) Vol.9 Issue 1, pp.100-107

Document Type:

Article

Publication Date:

1/2012

Document Language:

English

Document ID (Org No.):

2001388812

pISSN:

2309-4524

DOI:

10.34028/iajit