Difference between revisions of "Publications/robert-seidowsky.15.visapp"
From LRDE
(Created page with "{{Publication | published = true | date = 2015-03-01 | authors = Myriam Robert-Seidowsky, Jonathan Fabrizio, Séverine Dubuisson | title = TextTrail: A Robust Text Tracking Al...") |
|||
Line 7: | Line 7: | ||
| urllrde = 201410-VISAPPb |
| urllrde = 201410-VISAPPb |
||
| 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. |
||
− | | optlrdepaper = http://www.lrde.epita.fr/dload/papers/robert-seidowsky.15.visapp.pdf |
||
| note = accepted |
| note = accepted |
||
| type = inproceedings |
| type = inproceedings |
||
Line 36: | Line 35: | ||
without needing another one to reinitialize the tracking |
without needing another one to reinitialize the tracking |
||
model.<nowiki>}</nowiki>, |
model.<nowiki>}</nowiki>, |
||
− | optlrdepaper = <nowiki>{</nowiki>http://www.lrde.epita.fr/dload/papers/robert-seidowsky.15.visapp.pdf<nowiki>}</nowiki> |
||
− | , |
||
note = <nowiki>{</nowiki>accepted<nowiki>}</nowiki> |
note = <nowiki>{</nowiki>accepted<nowiki>}</nowiki> |
||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
Revision as of 21:11, 16 January 2015
- Authors
- Myriam Robert-Seidowsky, Jonathan Fabrizio, Séverine Dubuisson
- Where
- Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISAPP)
- Type
- inproceedings
- Date
- 2015-03-01
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.
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}, 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.}, note = {accepted} }