A Novel Object Tracking Based on Foreground Hue Histogram

Yun Gao; Hao Zhou; Xue Jie Zhang

doi:10.4028/www.scientific.net/AMM.278-280.1205

Paper Titles

Edge Detection with Information Measure and Support Vector Machine
p.1187

Research on Importance of Texture Information in Face Recognition
p.1193

Research on Key Technology of 2D Barcode in Identity Authentication
p.1197

The Ancient Ceramics Identification Methods Based on Non-Linear Support Vector Machines
p.1201

A Novel Object Tracking Based on Foreground Hue Histogram
p.1205

Application of Gabor Dictionary and SL0 Norm in Disguise Face Recognition
p.1211

Applying More Initial Groups to the Semi-Supervised Clustering Based on one-Class Support Vector Machines
p.1215

Color Image Super-Resolution Reconstruction Based on Sparse Representation
p.1221

Personal Identification by Fusing Hand Shape Geometry and Palmprint Features
p.1228

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280A Novel Object Tracking Based on Foreground Hue...

A Novel Object Tracking Based on Foreground Hue Histogram

Abstract:

We propose a tracking algorithm for a single non-rigid object based on its foreground hue histogram. A tracked region can be described by the foreground hue histogram only calculating foreground object pixels, which can effectively restrain the disturbing of complex background environments. For measuring the object likelihood, we match the foreground hue histogram with that of the tracked object and refer the result of motion detection to encircle the tracked object region as much as possible. During the tracking, we update the hue histogram model for adapting the object appearance variation. The proposed algorithm is realized in the particle filter frame, and the experiments show that it is capable of robustly and accurately tracking a single non-rigid object for the situations of complex background scenes and strong appearance variations.