Appearance-based tracking and recognition using the 3D trilinear tensor

Author

Shao, Jie ; Zhou, Shaohua Kevin ; Chellappa, Rama

Author_Institution

Center for Autom. Res., Maryland Univ., College Park, MD, USA

Volume

3

fYear

2004

fDate

17-21 May 2004

Abstract

The paper presents an appearance-based adaptive algorithm for simultaneous tracking and recognition by generalizing the transformation model to 3D perspective transformation. A trilinear tensor operator is used to represent the 3D geometrical structure. The tensor is estimated by predicting the corresponding points using the existing affine-transformation based algorithm. The estimated tensor is used to synthesize novel views to update the appearance templates. Some experimental results using airborne video are presented.

Keywords

adaptive estimation; image recognition; image representation; mathematical operators; tensors; tracking; video signal processing; 3D geometrical structure representation; 3D perspective transformation; 3D trilinear tensor; adaptive algorithm; affine-transformation based prediction; airborne video; appearance template updating; appearance-based tracking; novel view synthesis; recognition; tensor estimation; trilinear tensor operator; video-based object tracking; Adaptive algorithm; Automation; Computer graphics; Computer vision; Educational institutions; Equations; Lighting; Particle filters; Stability; Tensile stress;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1326619

Filename

1326619