Particle Filer Tracking Algorithm Based on Fusion of Color Correlogram and SIFT Features
LIU Yuanlong
LI Yuhui
Abstract：This paper proposes a tracking algorithm based on particle filter algorithm with color correlogram and SIFT features.In the process of tracking,this algorithm has attractive result to resolve the problem of target losing no matter when the target was obscured or when target deformation occurred.The tracking effect is especially improved when moving target is similar to background in color.To evaluate different color correlation between prediction and observation state,the algorithm adopts color correlogram as one describe feature.To overcome the affine change characteristics of target,the SIFT feature is also adopted.With the color correlogram and SIFT features fusion,both the reliability of features description and accuracy of tracking is improved.This algorithm is superior to the traditional particle filter tracking algorithm.
Keywords：color correlogramSIFTparticle filterfeature fusion
Publication Date：2016-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1246-1249,1292 )