Adaptive Alignment of Non-target Cluster Centers to Background -- Improvement of Robustness and Processing Speed for K-means tracker --

Hiroshi OIKE  Haiyuan WU  Toshikazu WADA 

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)  Vol.J91-D  No.9  pp.2418-2421
Publication Date: 2008/09/01
Online ISSN: 1881-0225
Print ISSN: 1880-4535
Type of Manuscript: LETTER
Category: 
Keyword: 
K-means tracker,  object tracking, 

Full Text(in Japanese): PDF(386.5KB)

Summary: 
We present a method for adequate alignment of non-target cluster centers for K-means tracker algorithm. In this method, the number of non-target cluster centers and alignment of them are determined based on the distances from a pixel which is on the ellipse surrounding a target to both target cluster centers and non-target cluster centers. This distance is calculated in the 5 dimensional feature space used in K-means tracker. This method can prevent selecting the pixel as a non-target cluster center which doesn't contribute to clustering for tracking a target or which has similar feature with other determined non-target cluster centers. Through a comparative object tracking experiment, we confirmed that this algorithm contributes stabilization of object tracking and improvement of efficient processing.