Research on an improved visual background extraction algorithm

XU Yun; PENG Yong; HU Min-tao

doi:10.13873/j.1000-9787(2018)03-0038-03

Chinese

您当前的位置：

首页 >

文章列表页 >

Research on an improved visual background extraction algorithm

更新时间：2025-09-11

- Research on an improved visual background extraction algorithm
- Vol. 37, Issue 3, Pages: 38-40+43(2018)
- 作者机构：
  
  江南大学物联网工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-9787(2018)03-0038-03
  CLC： TP391.41
- Published：2018
- 稿件说明：
移动端阅览
[1]徐赟,彭勇,胡旻涛.一种改进的视觉背景提取算法研究[J].传感器与微系统,2018,37(03):38-40+43.

XU Yun, PENG Yong, HU Min-tao. Research on an improved visual background extraction algorithm[J]. 2018, 37(3): 38-40+43.
[1]徐赟,彭勇,胡旻涛.一种改进的视觉背景提取算法研究[J].传感器与微系统,2018,37(03):38-40+43. DOI： 10.13873/j.1000-9787(2018)03-0038-03.

XU Yun, PENG Yong, HU Min-tao. Research on an improved visual background extraction algorithm[J]. 2018, 37(3): 38-40+43. DOI： 10.13873/j.1000-9787(2018)03-0038-03.

摘要

针对视觉背景提取（Vi Be）算法在初始化背景模型时易产生鬼影以及对户外动态场景适应能力差、检测精度低等问题

在算法初始化阶段

通过采用前景点计数的方法

统计静止像素点占前景块的百分比

有效抑制了鬼影的产生

提高了算法检测精度;在前景检测阶段

根据场景的动态程度自适应调整阈值

提高了算法对动态背景的适应能力。实验表明:与原算法相比

在动态场景中算法检测精度提高了20%以上。

Abstract

Aiming at problem that visual background extraction（ Vi Be） algorithm is prone to produce ghost when initializing the background model and its adaptability is poor in outdoor dynamic scenes and the detection precision is low

an improved visual background extraction algorithm is proposed. In initial stage of the algorithm

to improve precision of the algorithm

the ghost is effectively suppressed by counting the percentage of still pixels in foreground blocks. In the foreground detection stage

improve the adaptability in dynamic scenes

dynamically adjust threshold according to the scene dynamic degree. Experimental results demonstrate that precision of this algorithm is improved by 20 % compared with the original Vi Be algorithm.

关键词

Keywords

references

全局运动补偿的动态背景下运动轨迹跟踪算法 [J]. 王闪,吴秦. 传感器与微系统 . 2016(08)

面向运动目标检测的ViBe算法改进 [J]. 徐久强,江萍萍,朱宏博,左伟. 东北大学学报(自然科学版) . 2015(09)

基于灰度特征和自适应阈值的虚拟背景提取研究 [J]. 庄哲民,章聪友,杨金耀,李芬兰. 电子与信息学报 . 2015(02)

混合高斯背景模型目标检测的一种改进算法 [J]. 邱联奎,刘启亮,赵予龙,李冠杰. 计算机仿真 . 2014(05)

改进视觉背景提取模型的运动目标检测算法 [J]. 苏延召,李艾华,姜柯,金广智. 计算机辅助设计与图形学学报 . 2014(02)

一种基于Kalman滤波器的自适应背景建模改进算法 [J]. 伍健荣,杜向龙,刘海涛. 传感器与微系统 . 2012(01)

Real-time foreground–background segmentation using codebook model [J] . Kyungnam Kim,Thanarat H. Chalidabhongse,David Harwood,Larry Davis. Real-Time Imaging . 2005 (3)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design of adaptive threshold edge detection system based on FPGA

Threshold self-adaptive optimizing de-noising method based on wavelet transform

Fault diagnosis for pitch system of wind turbines based on multi-model PF

Image segmentation method of industrial fumes based on background modeling and feature matching

UAV aerial image fast mosaic algorithm in maritime supervision

Related Author

SUN Lei

WEI Min

YANG Kang

CHEN Guangwu

NING Zheng

ZHANG Zhaoxin

NIU Hongxia

WANG Jinhua

Related Institution

School of Electrical and Automation,Anhui University

Automatic Control Institute,Lanzhou Jiaotong University

Gansu Provincial Key Laboratory of Traffic Information Engineering and Control

College of Computer and Communication,Lanzhou University of Technology

College of Electrical and Information Engineering,Lanzhou University of Technology

⁰