Object rotation tracking based on kernelized correlation filters

LI Long; WANG Yao-nan; ZHANG Zhen-jun

doi:10.13873/J.1000-9787(2017)03-0147-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Object rotation tracking based on kernelized correlation filters

更新时间：2025-09-11

- Object rotation tracking based on kernelized correlation filters
- Vol. 36, Issue 3, Pages: 147-149+160(2017)
- 作者机构：
  
  1. 机器人视觉感知与控制技术国家工程实验室
  2. 湖南大学电气与信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2017)03-0147-03
  CLC： TN713;TP391.41
- Published：2017
- 稿件说明：
移动端阅览
[1]李龙,王耀南,张振军.基于核相关滤波器的目标旋转跟踪算法[J].传感器与微系统,2017,36(03):147-149+160.

LI Long, WANG Yao-nan, ZHANG Zhen-jun. Object rotation tracking based on kernelized correlation filters[J]. 2017, 36(3): 147-149+160.
[1]李龙,王耀南,张振军.基于核相关滤波器的目标旋转跟踪算法[J].传感器与微系统,2017,36(03):147-149+160. DOI： 10.13873/J.1000-9787(2017)03-0147-03.

LI Long, WANG Yao-nan, ZHANG Zhen-jun. Object rotation tracking based on kernelized correlation filters[J]. 2017, 36(3): 147-149+160. DOI： 10.13873/J.1000-9787(2017)03-0147-03.

摘要

提出一种新的鲁棒的旋转估计算法

以核相关滤波器理论为基础

通过在目标中心等角度间隔来采样一个样本金字塔

单独训练一个一维的角度估计滤波器

从而将目标旋转角估计问题变为一个检测问题。提出的角度估计方法具有通用性

可以辅助其它没有角度估计功能的跟踪器。在实验中

单独训练一个位移跟踪滤波器和一个尺度估计滤波器

结合本文提出的角度估计滤波器形成一个由三层滤波器组成的跟踪器。和经典的算法在不同测试数据上的对比实验表明

该算法能达到较高的跟踪精度。

Abstract

A new robust rotation estimation method is proposed

which is based on kernelized correlation filters. A rotation pyramid is sampled around the target center and an extra 1D rotation filter is trained. Then the rotation estimation problem is tackled in a tracking-by-detection way. The rotation estimation approach is generic and can be incorporated with any tracking algorithm without a rotation estimation scheme. In the experiment

a three-layerbased tracker consisting of a 2D translation filter

a 1D scale filter and a 1D rotation filter is proposed trained and demonstrated to achieve more accurate results against state-of-the-arts on challenging dataset with rotation variation.

关键词

Keywords

references

Robust Kalman tracking and smoothing with propagating and non-propagating outliers [J] . Peter Ruckdeschel,Bernhard Spangl,Daria Pupashenko. Statistical Papers . 2014 (1)

A new distance measure based on generalized Image Normalized Cross-Correlation for robust video tracking and image recognition [J] . Arie Nakhmani,Allen Tannenbaum. Pattern Recognition Letters . 2013 (3)

An adaptive color-based particle filter [J] . Katja Nummiaro,Esther Koller-Meier,Luc Van Gool. Image and Vision Computing . 2002 (1)

Views

196

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-level association object tracking algorithm based on 3D LiDAR sensor

Long-time moving target tracking method integrating HOG and color feature

Adaptive target tracking algorithm based on ELM and KCF

Microminiature parts tracking system based on micro-vision

Improved SURF algorithm and its application in object tracking

Related Author

TANG Xiangyang

HU Gonglin

LIU Hui

SHANG Zhenhong

CHEN Qiang

HAN Kun

LI Yaotong

PAN Difu

Related Institution

Library，Wuhan City Vocational College

School of Mathematics and Statistics,Central China Normal University

Faculty of Information Engineering and Automation,Kunming University of Science and Technology

School of Traffic and Transportation Engineering,Central South University

School of Computer & Information Engineering,Beijing Technology and Business University

⁰