Difference between revisions of "Publications/robert-seidowsky.15.visapp"

From LRDE

Line 5: Line 5:
 
| title = TextTrail: A Robust Text Tracking Algorithm In Wild Environments
 
| title = TextTrail: A Robust Text Tracking Algorithm In Wild Environments
 
| booktitle = Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISAPP)
 
| booktitle = Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISAPP)
| pages = 268–276
+
| pages = 268 to 276
 
| abstract = In this paper, we propose TextTrail, a robust new algorithm dedicated to text tracking in uncontrolled environments (strong motion of camera and objects, partial occlusions, blur, etc.). It is based on a particle filter framework whose correction step has been improved. Firstwe compare some likelihood functions and introduce a new one that integrates tangent distance. We show that the likelihood function has a strong influence on the text tracking performances. Secondly, we compare our tracker with another and finally present an example of application. TextTrail has been tested on real video sequences and has proven its efficiency. In particular, it can track texts in complex situations starting from only one detection step without needing another one to reinitialize the tracking model.
 
| abstract = In this paper, we propose TextTrail, a robust new algorithm dedicated to text tracking in uncontrolled environments (strong motion of camera and objects, partial occlusions, blur, etc.). It is based on a particle filter framework whose correction step has been improved. Firstwe compare some likelihood functions and introduce a new one that integrates tangent distance. We show that the likelihood function has a strong influence on the text tracking performances. Secondly, we compare our tracker with another and finally present an example of application. TextTrail has been tested on real video sequences and has proven its efficiency. In particular, it can track texts in complex situations starting from only one detection step without needing another one to reinitialize the tracking model.
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/robert-seidowsky.15.visapp.pdf
 
| lrdepaper = http://www.lrde.epita.fr/dload/papers/robert-seidowsky.15.visapp.pdf

Revision as of 17:57, 4 January 2018

Abstract

In this paper, we propose TextTrail, a robust new algorithm dedicated to text tracking in uncontrolled environments (strong motion of camera and objects, partial occlusions, blur, etc.). It is based on a particle filter framework whose correction step has been improved. Firstwe compare some likelihood functions and introduce a new one that integrates tangent distance. We show that the likelihood function has a strong influence on the text tracking performances. Secondly, we compare our tracker with another and finally present an example of application. TextTrail has been tested on real video sequences and has proven its efficiency. In particular, it can track texts in complex situations starting from only one detection step without needing another one to reinitialize the tracking model.

Documents

Bibtex (lrde.bib)

@InProceedings{	  robert-seidowsky.15.visapp,
  author	= {Myriam Robert-Seidowsky and Jonathan Fabrizio and
		  S\'everine Dubuisson},
  title		= {{TextTrail:} A Robust Text Tracking Algorithm In Wild
		  Environments},
  booktitle	= {Proceedings of the 10th International Conference on
		  Computer Vision Theory and Applications (VISAPP)},
  month		= mar,
  year		= {2015},
  pages		= {268--276},
  abstract	= {In this paper, we propose TextTrail, a robust new
		  algorithm dedicated to text tracking in uncontrolled
		  environments (strong motion of camera and objects, partial
		  occlusions, blur, etc.). It is based on a particle filter
		  framework whose correction step has been improved. First,
		  we compare some likelihood functions and introduce a new
		  one that integrates tangent distance. We show that the
		  likelihood function has a strong influence on the text
		  tracking performances. Secondly, we compare our tracker
		  with another and finally present an example of application.
		  TextTrail has been tested on real video sequences and has
		  proven its efficiency. In particular, it can track texts in
		  complex situations starting from only one detection step
		  without needing another one to reinitialize the tracking
		  model.}
}