Particle Filtering Based Visual Attention Model for Moving Target Detection

LIU Long; FAN Bo-yang; LIU Jin-xing; YANG Le-chao

doi:10.3969/j.issn.0372-2112.2016.09.031

您当前的位置：

首页 >

文章列表页 >

Particle Filtering Based Visual Attention Model for Moving Target Detection

更新时间：2025-07-16

- Particle Filtering Based Visual Attention Model for Moving Target Detection
- Acta Electronica Sinica Vol. 44, Issue 9, Pages: 2235-2241(2016)
- 作者机构：
  
  西安理工大学自动化学院,陕西,西安,710048
- 作者简介：
- 基金信息：
  
  Industrial Science and Technology Research and Development Project of Shaanxi Province (NO.2016GY-128);National Natural Science Foundation of China (No.61001140);Technology Transfer Promotion Project of of Xi'an Science and Technology Bureau (No.CX12166)
- DOI：10.3969/j.issn.0372-2112.2016.09.031
  CLC： TN911.7
- Published Online：25 September 2016，
  
  Published：2016
- 稿件说明：
移动端阅览
LIU Long, FAN Bo-yang, LIU Jin-xing, et al. Particle Filtering Based Visual Attention Model for Moving Target Detection[J]. Acta Electronica Sinica, 2016, 44(9): 2235-2241.
DOI：

LIU Long, FAN Bo-yang, LIU Jin-xing, et al. Particle Filtering Based Visual Attention Model for Moving Target Detection[J]. Acta Electronica Sinica, 2016, 44(9): 2235-2241. DOI： 10.3969/j.issn.0372-2112.2016.09.031.

摘要

视觉注意力是机器视觉领域的研究热点，对目标检测、跟踪等技术发展具有积极意义，本文面向运动目标检测问题，构建了一种基于粒子滤波的视觉注意力模型.首先依据贝叶斯估计理论，推导了基于注意力的粒子权重计算方法；然后将运动注意力和目标颜色注意力分别作为自底向上（Bottom-Up）和自顶向下（Top-Down）注意力的输入，通过重要性采样、粒子权值计算、重采样等形成粒子注意力显著图，并确定目标位置；测试结果显示本文方法能够获取比其它方法更好的目标注意力显著图，并具有准确的目标检测效果.

Abstract

Visual attention is one of the research hotspots in the field of machine vision

which is positive significance for development of target detection and target tracking.This paper presents a particle filter based visual attention model that is applied to detect moving target.Firstly

according to Bayes estimation theory

the method of particle weight calculation is established by visual bidirectional (Top-Down/Bottom-Up) fusion attention.Then motion attention and target color attention are adopted as input of the attention model

and moving target saliency is calculated through the importance sampling

particle weight calculation

resampling and particle saliency map processing.Lastly

the target position is determined by distribution of particle.Different video complex scene test results show that this method is more effective and accurate than the traditional method for detection of moving target.

关键词

Keywords

references

Views

408

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Temporal-Pulse Amplitude Clustering-Based Unknown Radar Emitter Signal Sorting Method

A Likelihood-Ratio Detection Method of Radar Target Based on Particle Filtering

A Novel Particle Filtering Algorithm Based on Generalized Unscented Transformation

Neighborhood Definition for Catadioptric Omnidirectional Image Based on Resolution of Position

Related Author

XIE Kai

LIN Zi-han

SUN Hui-bo

HUANG Ming-jun

LIN Jin-jian

FONT

YU Xing-Wei

Related Institution

The 29th Research Institute of China Electronics Technology Group Corporation

Deptment of Electronics and Communication Engineering, Sun Yat-sen University of China

Wuhan Radar Institute

(College of Automation, Northwestern Polytechnical University,,,)

College of Information Systems and Management, National University of Defense Technology

⁰