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...") |
|||
(10 intermediate revisions by the same user not shown) | |||
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 to 276 |
||
− | | 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. |
||
− | | |
+ | | lrdepaper = http://www.lrde.epita.fr/dload/papers/robert-seidowsky.15.visapp.pdf |
+ | | lrdeprojects = Olena |
||
− | | note = accepted |
||
| type = inproceedings |
| type = inproceedings |
||
| id = robert-seidowsky.15.visapp |
| id = robert-seidowsky.15.visapp |
||
+ | | identifier = doi:10.5220/0005292002680276 |
||
| bibtex = |
| bibtex = |
||
@InProceedings<nowiki>{</nowiki> robert-seidowsky.15.visapp, |
@InProceedings<nowiki>{</nowiki> robert-seidowsky.15.visapp, |
||
author = <nowiki>{</nowiki>Myriam Robert-Seidowsky and Jonathan Fabrizio and |
author = <nowiki>{</nowiki>Myriam Robert-Seidowsky and Jonathan Fabrizio and |
||
S\'everine Dubuisson<nowiki>}</nowiki>, |
S\'everine Dubuisson<nowiki>}</nowiki>, |
||
− | title = <nowiki>{</nowiki><nowiki>{</nowiki>TextTrail<nowiki>}</nowiki>: A Robust Text Tracking Algorithm In Wild |
+ | title = <nowiki>{</nowiki><nowiki>{</nowiki>TextTrail<nowiki>}</nowiki>: <nowiki>{</nowiki>A<nowiki>}</nowiki> Robust Text Tracking Algorithm In Wild |
Environments<nowiki>}</nowiki>, |
Environments<nowiki>}</nowiki>, |
||
booktitle = <nowiki>{</nowiki>Proceedings of the 10th International Conference on |
booktitle = <nowiki>{</nowiki>Proceedings of the 10th International Conference on |
||
Line 21: | Line 22: | ||
month = mar, |
month = mar, |
||
year = <nowiki>{</nowiki>2015<nowiki>}</nowiki>, |
year = <nowiki>{</nowiki>2015<nowiki>}</nowiki>, |
||
⚫ | |||
abstract = <nowiki>{</nowiki>In this paper, we propose TextTrail, a robust new |
abstract = <nowiki>{</nowiki>In this paper, we propose TextTrail, a robust new |
||
algorithm dedicated to text tracking in uncontrolled |
algorithm dedicated to text tracking in uncontrolled |
||
Line 36: | Line 38: | ||
without needing another one to reinitialize the tracking |
without needing another one to reinitialize the tracking |
||
model.<nowiki>}</nowiki>, |
model.<nowiki>}</nowiki>, |
||
− | + | doi = <nowiki>{</nowiki>10.5220/0005292002680276<nowiki>}</nowiki> |
|
− | , |
||
⚫ | |||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Latest revision as of 17:01, 27 May 2021
- Authors
- Myriam Robert-Seidowsky, Jonathan Fabrizio, Séverine Dubuisson
- Where
- Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISAPP)
- Type
- inproceedings
- Projects
- Olena
- 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.
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.}, doi = {10.5220/0005292002680276} }