A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform

Antoine Tran; Antoine Manzanera

doi:10.1109/IPTA.2015.7367106

A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform

Antoine Tran, Antoine Manzanera

Université Paris-Saclay

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper introduces a new object tracking method which combines two algorithms working in parallel, and based on low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based description, and the Particle Filter, using a global description. The object model is updated by combining information from a back-projection map computed from the Generalised Hough Transform, providing for every pixel the degree to which it may belong to the object, and from the Particle Filter, providing a probability density on the global object state. The purpose of the proposed tracker is to make the most of the two algorithms, in terms of robustness to appearance variation like scaling, rotation, non-rigid deformation or illumination changes.

Original language	English
Title of host publication	5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015
Editors	Rachid Jennane
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	105-110
Number of pages	6
ISBN (Electronic)	9781479986354
DOIs	https://doi.org/10.1109/IPTA.2015.7367106
Publication status	Published - 28 Dec 2015
Externally published	Yes
Event	5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015 - Orleans, France Duration: 10 Nov 2015 → 13 Nov 2015

Publication series

Name	5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015

Conference

Conference	5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015
Country/Territory	France
City	Orleans
Period	10/11/15 → 13/11/15

Keywords

Colour and Edge Features
Generalised Hough Transform
Object Tracking
Particle Filter

Access to Document

10.1109/IPTA.2015.7367106

Cite this

Tran, A., & Manzanera, A. (2015). A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform. In R. Jennane (Ed.), 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015 (pp. 105-110). Article 7367106 (5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPTA.2015.7367106

Tran, Antoine ; Manzanera, Antoine. / A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform. 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015. editor / Rachid Jennane. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 105-110 (5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015).

@inproceedings{8092ce0409384b6f90a9fd0335a035ae,

title = "A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform",

abstract = "This paper introduces a new object tracking method which combines two algorithms working in parallel, and based on low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based description, and the Particle Filter, using a global description. The object model is updated by combining information from a back-projection map computed from the Generalised Hough Transform, providing for every pixel the degree to which it may belong to the object, and from the Particle Filter, providing a probability density on the global object state. The purpose of the proposed tracker is to make the most of the two algorithms, in terms of robustness to appearance variation like scaling, rotation, non-rigid deformation or illumination changes.",

keywords = "Colour and Edge Features, Generalised Hough Transform, Object Tracking, Particle Filter",

author = "Antoine Tran and Antoine Manzanera",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015 ; Conference date: 10-11-2015 Through 13-11-2015",

year = "2015",

month = dec,

day = "28",

doi = "10.1109/IPTA.2015.7367106",

language = "English",

series = "5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "105--110",

editor = "Rachid Jennane",

booktitle = "5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015",

}

Tran, A & Manzanera, A 2015, A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform. in R Jennane (ed.), 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015., 7367106, 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015, Institute of Electrical and Electronics Engineers Inc., pp. 105-110, 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015, Orleans, France, 10/11/15. https://doi.org/10.1109/IPTA.2015.7367106

A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform. / Tran, Antoine; Manzanera, Antoine.
5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015. ed. / Rachid Jennane. Institute of Electrical and Electronics Engineers Inc., 2015. p. 105-110 7367106 (5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform

AU - Tran, Antoine

AU - Manzanera, Antoine

PY - 2015/12/28

Y1 - 2015/12/28

N2 - This paper introduces a new object tracking method which combines two algorithms working in parallel, and based on low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based description, and the Particle Filter, using a global description. The object model is updated by combining information from a back-projection map computed from the Generalised Hough Transform, providing for every pixel the degree to which it may belong to the object, and from the Particle Filter, providing a probability density on the global object state. The purpose of the proposed tracker is to make the most of the two algorithms, in terms of robustness to appearance variation like scaling, rotation, non-rigid deformation or illumination changes.

AB - This paper introduces a new object tracking method which combines two algorithms working in parallel, and based on low-level observations (colour and gradient orientation): the Generalised Hough Transform, using a pixel-based description, and the Particle Filter, using a global description. The object model is updated by combining information from a back-projection map computed from the Generalised Hough Transform, providing for every pixel the degree to which it may belong to the object, and from the Particle Filter, providing a probability density on the global object state. The purpose of the proposed tracker is to make the most of the two algorithms, in terms of robustness to appearance variation like scaling, rotation, non-rigid deformation or illumination changes.

KW - Colour and Edge Features

KW - Generalised Hough Transform

KW - Object Tracking

KW - Particle Filter

U2 - 10.1109/IPTA.2015.7367106

DO - 10.1109/IPTA.2015.7367106

M3 - Conference contribution

AN - SCOPUS:84963864878

T3 - 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015

SP - 105

EP - 110

BT - 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015

A2 - Jennane, Rachid

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015

Y2 - 10 November 2015 through 13 November 2015

ER -

Tran A, Manzanera A. A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform. In Jennane R, editor, 5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 105-110. 7367106. (5th International Conference on Image Processing, Theory, Tools and Applications 2015, IPTA 2015). doi: 10.1109/IPTA.2015.7367106

A versatile object tracking algorithm combining Particle Filter and Generalised Hough Transform

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this