Improved Object Tracking Algorithm Based on New HSV Color Probability Model

Authors:
Gang Tian;Ruimin Hu;Zhongyuan Wang;Youming Fu
Affiliations:
National Multimedia Software Engineering Research Center, Wuhan, China 430079;National Multimedia Software Engineering Research Center, Wuhan, China 430079;National Multimedia Software Engineering Research Center, Wuhan, China 430079;School of Computing, Wuhan University, Wuhan, China 430079
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Year:
2009

Citing 6
Cited 1

Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift Analysis and Applications

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Object tracking using CamShift algorithm and multiple quantized feature spaces

VIP '05 Proceedings of the Pan-Sydney area workshop on Visual information processing
Robust visual tracking for multiple targets

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking

IEEE Transactions on Signal Processing

Human tracking: a state-of-art survey

KES'10 Proceedings of the 14th international conference on Knowledge-based and intelligent information and engineering systems: Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an improved Cam-Shift algorithm is proposed. Traditional Cam-Shift algorithm only used H component in the HSV color space to build target color histogram, H color histogram is a relatively weak description of the characteristics of the target, so the algorithm is ineffective when the color distribution of the background and object is similar. Different with traditional algorithm, we building a new HSV combined color histogram model based on the character of human visual system, which is more sensitive to colors. The experiment results prove the new method can make a more accurate tracking result even in complex background.