Improved CAMshift based on supervised learning

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

1 Citation (Scopus)

Abstract

CAMshift algorithm refers on back-projected distribution of target object's colour to locate the location of the target object in the subsequent frame. However, this mechanism becomes inaccurate when one or more foreign objects that share the same colour features with the target object are very close to one another, resulting these objects are in the same search window. Therefore, this study proposed the embedment of two binary classifiers trained by SVM into the existing CAMshift. These classifiers were modeled to verify the back-projected distribution under 4 types of representations and to distinguish target and non target objects. The aim is to maintain the search window to cover only the target object during tracking. Experiments were conducted to verify the performance of the classifier under three environments namely easy, adjacent and cluttered. Results have shown that the classifier has managed to classify true detection with up to 80%.

Original languageEnglish
Title of host publicationAdvances in Intelligent Systems and Computing
Pages611-621
Number of pages11
Volume208 AISC
DOIs
Publication statusPublished - 2013
Event1st International Conference on Robot Intelligence Technology and Applications, RiTA 2012 - Gwangju
Duration: 16 Dec 201218 Dec 2012

Publication series

NameAdvances in Intelligent Systems and Computing
Volume208 AISC
ISSN (Print)21945357

Other

Other1st International Conference on Robot Intelligence Technology and Applications, RiTA 2012
CityGwangju
Period16/12/1218/12/12

Fingerprint

Supervised learning
Classifiers
Color
Experiments

Keywords

  • CAMshift
  • object tracking
  • Support Vector Machine

ASJC Scopus subject areas

  • Computer Science(all)
  • Control and Systems Engineering

Cite this

Zin, N. A. M., Sheikh Abdullah, S. N. H., & Abdullah, A. (2013). Improved CAMshift based on supervised learning. In Advances in Intelligent Systems and Computing (Vol. 208 AISC, pp. 611-621). (Advances in Intelligent Systems and Computing; Vol. 208 AISC). https://doi.org/10.1007/978-3-642-37374-9_58

Improved CAMshift based on supervised learning. / Zin, Nur Ariffin Mohd; Sheikh Abdullah, Siti Norul Huda; Abdullah, Azizi.

Advances in Intelligent Systems and Computing. Vol. 208 AISC 2013. p. 611-621 (Advances in Intelligent Systems and Computing; Vol. 208 AISC).

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

Zin, NAM, Sheikh Abdullah, SNH & Abdullah, A 2013, Improved CAMshift based on supervised learning. in Advances in Intelligent Systems and Computing. vol. 208 AISC, Advances in Intelligent Systems and Computing, vol. 208 AISC, pp. 611-621, 1st International Conference on Robot Intelligence Technology and Applications, RiTA 2012, Gwangju, 16/12/12. https://doi.org/10.1007/978-3-642-37374-9_58
Zin NAM, Sheikh Abdullah SNH, Abdullah A. Improved CAMshift based on supervised learning. In Advances in Intelligent Systems and Computing. Vol. 208 AISC. 2013. p. 611-621. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-642-37374-9_58
Zin, Nur Ariffin Mohd ; Sheikh Abdullah, Siti Norul Huda ; Abdullah, Azizi. / Improved CAMshift based on supervised learning. Advances in Intelligent Systems and Computing. Vol. 208 AISC 2013. pp. 611-621 (Advances in Intelligent Systems and Computing).
@inproceedings{f290d91e47714476a56bef5465e5ac2b,
title = "Improved CAMshift based on supervised learning",
abstract = "CAMshift algorithm refers on back-projected distribution of target object's colour to locate the location of the target object in the subsequent frame. However, this mechanism becomes inaccurate when one or more foreign objects that share the same colour features with the target object are very close to one another, resulting these objects are in the same search window. Therefore, this study proposed the embedment of two binary classifiers trained by SVM into the existing CAMshift. These classifiers were modeled to verify the back-projected distribution under 4 types of representations and to distinguish target and non target objects. The aim is to maintain the search window to cover only the target object during tracking. Experiments were conducted to verify the performance of the classifier under three environments namely easy, adjacent and cluttered. Results have shown that the classifier has managed to classify true detection with up to 80{\%}.",
keywords = "CAMshift, object tracking, Support Vector Machine",
author = "Zin, {Nur Ariffin Mohd} and {Sheikh Abdullah}, {Siti Norul Huda} and Azizi Abdullah",
year = "2013",
doi = "10.1007/978-3-642-37374-9_58",
language = "English",
isbn = "9783642373732",
volume = "208 AISC",
series = "Advances in Intelligent Systems and Computing",
pages = "611--621",
booktitle = "Advances in Intelligent Systems and Computing",

}

TY - GEN

T1 - Improved CAMshift based on supervised learning

AU - Zin, Nur Ariffin Mohd

AU - Sheikh Abdullah, Siti Norul Huda

AU - Abdullah, Azizi

PY - 2013

Y1 - 2013

N2 - CAMshift algorithm refers on back-projected distribution of target object's colour to locate the location of the target object in the subsequent frame. However, this mechanism becomes inaccurate when one or more foreign objects that share the same colour features with the target object are very close to one another, resulting these objects are in the same search window. Therefore, this study proposed the embedment of two binary classifiers trained by SVM into the existing CAMshift. These classifiers were modeled to verify the back-projected distribution under 4 types of representations and to distinguish target and non target objects. The aim is to maintain the search window to cover only the target object during tracking. Experiments were conducted to verify the performance of the classifier under three environments namely easy, adjacent and cluttered. Results have shown that the classifier has managed to classify true detection with up to 80%.

AB - CAMshift algorithm refers on back-projected distribution of target object's colour to locate the location of the target object in the subsequent frame. However, this mechanism becomes inaccurate when one or more foreign objects that share the same colour features with the target object are very close to one another, resulting these objects are in the same search window. Therefore, this study proposed the embedment of two binary classifiers trained by SVM into the existing CAMshift. These classifiers were modeled to verify the back-projected distribution under 4 types of representations and to distinguish target and non target objects. The aim is to maintain the search window to cover only the target object during tracking. Experiments were conducted to verify the performance of the classifier under three environments namely easy, adjacent and cluttered. Results have shown that the classifier has managed to classify true detection with up to 80%.

KW - CAMshift

KW - object tracking

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84876208526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876208526&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-37374-9_58

DO - 10.1007/978-3-642-37374-9_58

M3 - Conference contribution

AN - SCOPUS:84876208526

SN - 9783642373732

VL - 208 AISC

T3 - Advances in Intelligent Systems and Computing

SP - 611

EP - 621

BT - Advances in Intelligent Systems and Computing

ER -