Occlusion handling for object tracking using a fast level set method
Tracking objects in image sequences is a difficult problem because of the frequent occlusions encountered among the objects and people. In this paper, a method for tracking objects through occlusions based on a level set technique, is presented. Two cases are considered: 1-the object is obstructed b...
Guardado en:
Autores principales: | , , , , |
---|---|
Formato: | CONF |
Materias: | |
Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p61_Gambini |
Aporte de: |
id |
todo:paper_97807695_v_n_p61_Gambini |
---|---|
record_format |
dspace |
spelling |
todo:paper_97807695_v_n_p61_Gambini2023-10-03T16:42:50Z Occlusion handling for object tracking using a fast level set method Gambini, J. Rozichner, D. Buemi, M.E. Mejail, M. Berllés, J.J. Color Color image processing Computational geometry Computer graphics Curve fitting Digital image storage Image processing Imaging systems Level measurement Optical properties Active contours Classic algorithms Classical algorithms Curve fits Fast level set methods Image objects Image sequences Level set techniques Object of interests Object tracking Occlusion handlings Tracking objects Edge detection Tracking objects in image sequences is a difficult problem because of the frequent occlusions encountered among the objects and people. In this paper, a method for tracking objects through occlusions based on a level set technique, is presented. Two cases are considered: 1-the object is obstructed by another one of a different color. 2-the object is obstructed by another one of the same color. In the first case, the classical algorithms based on active contours fail to track the object's contour because the curve disappears from the scene. In this proposal, occlusion is detected and the solution is based on keeping the curve in the same place until the object of interest appears in the scene again. In the second case, the classic algorithms based on active contours do not distinguish between two image objects of the same color, so due to the possible changes in the topology, the curve fits the edge of both objects and it is divided. We solve this problem by means of localizing the centroid of the curve. The experimental results show that these methods significantly improve the tracking with occlusions. © 2008 IEEE. Fil:Gambini, J. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Buemi, M.E. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Mejail, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. CONF info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p61_Gambini |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
topic |
Color Color image processing Computational geometry Computer graphics Curve fitting Digital image storage Image processing Imaging systems Level measurement Optical properties Active contours Classic algorithms Classical algorithms Curve fits Fast level set methods Image objects Image sequences Level set techniques Object of interests Object tracking Occlusion handlings Tracking objects Edge detection |
spellingShingle |
Color Color image processing Computational geometry Computer graphics Curve fitting Digital image storage Image processing Imaging systems Level measurement Optical properties Active contours Classic algorithms Classical algorithms Curve fits Fast level set methods Image objects Image sequences Level set techniques Object of interests Object tracking Occlusion handlings Tracking objects Edge detection Gambini, J. Rozichner, D. Buemi, M.E. Mejail, M. Berllés, J.J. Occlusion handling for object tracking using a fast level set method |
topic_facet |
Color Color image processing Computational geometry Computer graphics Curve fitting Digital image storage Image processing Imaging systems Level measurement Optical properties Active contours Classic algorithms Classical algorithms Curve fits Fast level set methods Image objects Image sequences Level set techniques Object of interests Object tracking Occlusion handlings Tracking objects Edge detection |
description |
Tracking objects in image sequences is a difficult problem because of the frequent occlusions encountered among the objects and people. In this paper, a method for tracking objects through occlusions based on a level set technique, is presented. Two cases are considered: 1-the object is obstructed by another one of a different color. 2-the object is obstructed by another one of the same color. In the first case, the classical algorithms based on active contours fail to track the object's contour because the curve disappears from the scene. In this proposal, occlusion is detected and the solution is based on keeping the curve in the same place until the object of interest appears in the scene again. In the second case, the classic algorithms based on active contours do not distinguish between two image objects of the same color, so due to the possible changes in the topology, the curve fits the edge of both objects and it is divided. We solve this problem by means of localizing the centroid of the curve. The experimental results show that these methods significantly improve the tracking with occlusions. © 2008 IEEE. |
format |
CONF |
author |
Gambini, J. Rozichner, D. Buemi, M.E. Mejail, M. Berllés, J.J. |
author_facet |
Gambini, J. Rozichner, D. Buemi, M.E. Mejail, M. Berllés, J.J. |
author_sort |
Gambini, J. |
title |
Occlusion handling for object tracking using a fast level set method |
title_short |
Occlusion handling for object tracking using a fast level set method |
title_full |
Occlusion handling for object tracking using a fast level set method |
title_fullStr |
Occlusion handling for object tracking using a fast level set method |
title_full_unstemmed |
Occlusion handling for object tracking using a fast level set method |
title_sort |
occlusion handling for object tracking using a fast level set method |
url |
http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p61_Gambini |
work_keys_str_mv |
AT gambinij occlusionhandlingforobjecttrackingusingafastlevelsetmethod AT rozichnerd occlusionhandlingforobjecttrackingusingafastlevelsetmethod AT buemime occlusionhandlingforobjecttrackingusingafastlevelsetmethod AT mejailm occlusionhandlingforobjecttrackingusingafastlevelsetmethod AT berllesjj occlusionhandlingforobjecttrackingusingafastlevelsetmethod |
_version_ |
1782027875945283584 |