Multi-object recognition and tracking with feature points matching and spatial layout consistency

Author

Boujelbane, Ismail ; Said, Souheil Hadj ; Zaharia, Titus

Author_Institution

Inst. Mines-Telecom, Telecom SudParis, Evry, France

fYear

2014

fDate

7-10 Sept. 2014

Firstpage

355

Lastpage

359

Abstract

In this paper, we propose a simultaneous textured object recognition and localization approach designed to real-time mobile devices applications. Local interest points are extracted and classified with the help of a strong matching algorithm. The matching procedure is based on a strict verification of the spatial layout consistency of the considered interest points. The proposed approach is well suited for real-time multi objects tracking and yields precision/recall rates superior to 90%.

Keywords

image matching; image texture; mobile handsets; object recognition; real-time systems; target tracking; feature points matching; local interest points; localization approach; multiobject recognition; multiobject tracking; precision rates; real-time mobile devices applications; recall rates; simultaneous textured object recognition; spatial layout consistency; Algorithm design and analysis; Feature extraction; Layout; Mobile handsets; Object recognition; Training; Visualization; layout consistency; local interest point; localization; matching pair;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics ??? Berlin (ICCE-Berlin), 2014 IEEE Fourth International Conference on

Conference_Location

Berlin

Type

conf

DOI

10.1109/ICCE-Berlin.2014.7034321

Filename

7034321