Enhanced image feature extraction for object tracking

Author

Charalampidis, Dimitrios ; Jilkov, Vesselin P. ; Nguyen, Trang M.

Author_Institution

Dept. of Electr. Eng., New Orleans Univ., LA, USA

Volume

2

fYear

2005

fDate

25-28 July 2005

Abstract

A feature-based technique is presented for 3D motion and structure estimation of rigid objects from a sequence of images. Considered is a feature-based rigid object representation which is more complete as compared to previous techniques. In this approach the features provide information regarding the location and type of significant object components and connections. A robust enhanced Hough transform (HT) approach is proposed for line and junction detection. Based on a perspective projection imaging model the extracted feature points of an object are for estimating its 3D motion and structure parameters by means of the unscented Kalman filter (UKF). The performances of the HT-based feature extractor and the UKF are illustrated via simulation results.

Keywords

Hough transforms; Kalman filters; feature extraction; image representation; motion estimation; object detection; target tracking; 3D motion estimation; Hough transform approach; UKF; feature-based rigid object representation; image feature extraction; object tracking; perspective projection imaging model; unscented Kalman filter; Data mining; Feature extraction; Motion estimation; Nonlinear optics; Optical filters; Optical signal processing; Robustness; Signal processing algorithms; State estimation; Target tracking; 3D Motion Estimation; Feature Extraction; Hough Transform; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Fusion, 2005 8th International Conference on

Print_ISBN

0-7803-9286-8

Type

conf

DOI

10.1109/ICIF.2005.1592042

Filename

1592042