基于遗传算法的背景提取算法

冀小平; 谢克明

您当前的位置：

首页 >

文章列表页 >

基于遗传算法的背景提取算法

更新时间：2026-09-14

- 基于遗传算法的背景提取算法
- 基于遗传算法的背景提取算法
- Issue 5, (2009)
- 作者机构：
  
  太原理工大学信息工程学院,山西,太原,030024
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2009
- 稿件说明：
移动端阅览
冀小平, 谢克明. 基于遗传算法的背景提取算法[J]. 2009, (5).
DOI：

冀小平, 谢克明. 基于遗传算法的背景提取算法[J]. 2009, (5). DOI：

摘要

针对视频图像处理中传统背景提取算法在时间复杂度和空间复杂度兼顾性能较差的缺点

提出一种基于遗传算法的背景重构算法.即在假设背景以最大概率出现在图像序列中的前提下

选择出现频率最高的图像作为背景图像.算法通过将图像分割成子图像

并将子图像参数化再进行统计

达到减低时间复杂度和空间复杂度的目的.仿真结果表明:在运动目标有较长的暂时停顿的情况下

该算法进行实时背景重构具有明显的优点;该算法能够准确地重构背景

并有效地避免混合现象

与直方图法相比

在不增加时间复杂度的情况下

空间复杂度可以减低到约1/50.

Abstract

Time complexity and space complexity weren't given consideration at the same time in the traditional background extraction algorithm for video image processing.Then a background reconstruction algorithm was presented based on the genetic algorithm.On the premise that background appeared in the image sequence with the greatest probability

the image appeared with the highest frequency was selected as a background image.The algorithm divided the image into sub-image

and made the sub-image parameterized

and then counted to reduce the time complexity and space complexity.Simulation results show that the real-time background reconstruction algorithm has obvious advantages when the moving targets have longer temporary stops.The algorithm can accurately reconstruct the background

and effectively avoid mixing phenomenon.Compared with the histogram method

the space complexity can be reduced to 1/50 without increasing the time complexity.

关键词

Keywords

references

Views

166

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Modeling and Validation of Lithium Battery Aging-Electrochemical-Thermal Behavior Based on SEI Film Thickening

基于Optuna优化的遗传算法智能组卷模型

Genetic Algorithm Optimized BP Neural Network for High⁃Speed Signal State Judgment

基于特征融合与SVM的内镜图像分类算法研究

A Shock Wave Testing System for High⁃Altitude Explosion Experiments

Related Author

LI Qi

DONG Xiaorui

LI Xiaojie

CHANG Chen

HU Anbo

GAO Peng

XIE Rui

WAN Chao

Related Institution

School of Energy and Power Engineering， North University of China

Shanxi Key Laboratory of High-end Equipment Reliability Technology， North University of China

Key Laboratory of Instrumentation Science and Dynamic Measurement（North University of China）， Ministry of Education

School of Electrical and Control Engineering， North University of China

⁰