A New Improvement on Mean-Shift Algorithm

Complex motion makes consecutive frames experience dramatic change, and thus becomes a barrier to object-tracking. Three factors contribute to more complexity of motion: longer sampling period,an moving object with complex appearance and nonrestraint movement, occlusion, which causes mean shift algo...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhong-Sheng Li, Ren-Fa Li, Yu-Feng Liu, Yao-Xue Zhang
Format: Conference Proceeding
Language:English
Subjects:
Computer science
Convergence
Kernel
Lighting
Merging
Q measurement
Sampling methods
Signal processing algorithms
Statistical analysis
Target tracking
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Complex motion makes consecutive frames experience dramatic change, and thus becomes a barrier to object-tracking. Three factors contribute to more complexity of motion: longer sampling period,an moving object with complex appearance and nonrestraint movement, occlusion, which causes mean shift algorithm losing its target due to too low a Bhattacharyya coefficient. To treat it, mean shift algorithm is improved based on a new way of fast color thresholding and region merging in this paper. Visual experiments show the effectiveness of the proposed method.
DOI:10.1109/CISP.2008.358