计算机与数字工程2016，Vol.45Issue(7)：1246-1249,1292,5.DOI:10.3969/j.issn.1672-9722.2016.07.012
基于色彩相关直方图与SIFT特征融合的粒子滤波跟踪算法
Particle Filer Tracking Algorithm Based on Fusion of Color Correlogram and SIFT Features
刘元龙 1李玉惠1
作者信息
- 1. 昆明理工大学信息工程与自动化学院 昆明 650500
- 折叠
摘要
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.关键词
色彩相关直方图/SIFT/粒子滤波/信息融合Key words
color correlogram/SIFT/particle filter/feature fusion分类
信息技术与安全科学引用本文复制引用
刘元龙,李玉惠..基于色彩相关直方图与SIFT特征融合的粒子滤波跟踪算法[J].计算机与数字工程,2016,45(7):1246-1249,1292,5.
