Multi-Classifier Object Tracking Based on Cluster Similarity

LI Kang; HE Fa-zhi; PAN Yi-teng; SUN Hang

doi:10.3969/j.issn.0372-2112.2016.04.010

您当前的位置：

首页 >

文章列表页 >

Multi-Classifier Object Tracking Based on Cluster Similarity

更新时间：2025-07-16

- Multi-Classifier Object Tracking Based on Cluster Similarity
- Acta Electronica Sinica Vol. 44, Issue 4, Pages: 821-825(2016)
- 作者机构：
  
  武汉大学计算机学院,湖北,武汉,430072
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2016.04.010
  CLC： TP391.41
- Published Online：25 April 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
LI Kang, HE Fa-zhi, PAN Yi-teng, et al. Multi-Classifier Object Tracking Based on Cluster Similarity[J]. Acta Electronica Sinica, 2016, 44(4): 821-825.
DOI：

LI Kang, HE Fa-zhi, PAN Yi-teng, et al. Multi-Classifier Object Tracking Based on Cluster Similarity[J]. Acta Electronica Sinica, 2016, 44(4): 821-825. DOI： 10.3969/j.issn.0372-2112.2016.04.010.

摘要

由于跟踪过程中目标和背景的变化

传统的单分类器跟踪算法学习到大量的非目标信息而导致跟踪精度降低.针对该问题

本文提出使用树形结构保存历史分类器.在每一帧

根据树中路径距离选择分类器集对测试样本分类.提出了一种基于簇相似性比较的分类算法.通过建立以方差为尺度的特征空间

比较测试样本到簇中心的距离计算相似度

快速计算出目标样本.实验表明本算法能够在复杂条件下实现对目标的鲁棒跟踪.

Abstract

Due to the changes of target and background during tracking

traditional single classifier tracking algorithms learn a lot of non-target information which result in the decrease of tracking accuracy.In this paper

we propose to use tree structure to save former classifiers as a set.In each frame

a subset of classifiers are chosen according to the path in the tree to classify test samples.We propose a classification algorithm based on cluster similarity comparison.A normalized feature space is established according to the variance of the cluster.The target in a new frame could be got by computing the distance between test samples and the center of the cluster.Experiments show that our algorithm could achieve the goal of robust tracking under complicated conditions.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Visual Object Tracking Algorithm Based on Adaptive Feature Selection

LiDAR Point Cloud Tracking Method Using Point-Voxel Relationship Modeling Under 3D Sparse Convolutional Framework

Correlation Filtering Tracking Algorithm Based on Adaptive Aspect-Ratio

Heterogeneous Online Multi-Source Transfer Learning with Cross-Domain Structure Preserving Projection

Object Tracking Algorithm Based on Dual-Model Competition Mechanism

Related Author

WANG Cai-xia

AN Qi

ZHOU Hong-ce

LI Yi-peng

TIAN Sheng-jing

HAN Yi-nan

ZHAO Xian-tong

LIU Xiu-ping

Related Institution

Jilin Province Technology Research Center of Photoelectric Detection and Intelligent Information Processing

School of Electronic Information and Engineering, Changchun University of Science and Technology

School of Mathematical Sciences, Dalian University of Technology

DUT-BSU Joint Institute, Dalian University of Technology

School of Economics and Management, China University of Mining and Technology

⁰