Probabilistic Matching Algorithm for Keypoint Based Object Tracking Using a Delaunay Triangulation

Author

Rémi, Trichet ; Bernard, Mérialdo

Author_Institution

Eurecom Inst., Sophia-Antipolis

fYear

2007

fDate

6-8 June 2007

Firstpage

17

Lastpage

17

Abstract

This article presents a matching algorithm developed for a generic object tracking system. Matching is a critical part for the effectiveness of tracking. The proposed method is a probabilistic algorithm inspired from the emerging "discriminative random fields". Points are associated according to their visual similarity and to spatial relations in their neighborhood, based on a Delaunay triangulation. Experimental results are presented to validate this contribution.

Keywords

image matching; mesh generation; object detection; probability; random processes; target tracking; Delaunay triangulation; discriminative random fields; keypoint based object tracking; probabilistic matching algorithm; spatial relation; visual similarity; Cost function; Image analysis; Image color analysis; Image motion analysis; Image texture analysis; Motion analysis; Sensor phenomena and characterization; TV receivers; Trajectory; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis for Multimedia Interactive Services, 2007. WIAMIS '07. Eighth International Workshop on

Conference_Location

Santorini

Print_ISBN

0-7695-2818-X

Electronic_ISBN

0-7695-2818-X

Type

conf

DOI

10.1109/WIAMIS.2007.69

Filename

4279125