[1]张钦礼,邱 杰,杨秀兰.改进的ViBe算法及其在运动目标检测中的应用[J].南京师大学报(自然科学版),2020,43(04):104-112.[doi:10.3969/j.issn.1001-4616.2020.04.015]
 Zhang Qinli,Qiu Jie,Yang Xiulan.Improved ViBe Algorithm and Its Application in Moving Objects Detection[J].Journal of Nanjing Normal University(Natural Science Edition),2020,43(04):104-112.[doi:10.3969/j.issn.1001-4616.2020.04.015]
点击复制

改进的ViBe算法及其在运动目标检测中的应用()
分享到:

《南京师大学报(自然科学版)》[ISSN:1001-4616/CN:32-1239/N]

卷:
第43卷
期数:
2020年04期
页码:
104-112
栏目:
·智慧应急信息技术·
出版日期:
2020-12-30

文章信息/Info

Title:
Improved ViBe Algorithm and Its Application in Moving Objects Detection
文章编号:
1001-4616(2020)04-0104-09
作者:
张钦礼邱 杰杨秀兰
玉林师范学院计算机科学与工程学院,广西,玉林 537000
Author(s):
Zhang QinliQiu JieYang Xiulan
College of Computer Science & Engineering,Yulin Normal University,Yulin 537000,China
关键词:
ViBe算法中位数分散度系数空间一致系数
Keywords:
ViBe algorithmmediandispersion coefficientspatial consistency coefficient
分类号:
TN911.73
DOI:
10.3969/j.issn.1001-4616.2020.04.015
文献标志码:
A
摘要:
针对ViBe算法用于运动目标检测时,前景提取结果容易出现鬼影、噪音以及检测结果不完整等问题,本文提出了一种改进的ViBe算法. 首先,利用多帧图像的中位数代替单帧图像对背景模型进行初始化; 第二,引入分散度系数构造自适应半径阈值代替原来固定的距离判定阈值; 第三,引入空间一致系数构造动态自适应更新因子代替原来固定更新因子. 实验结果表明:与传统及改进的ViBe算法相比,本文提出的算法能够适应动态背景及光照变化,有效抑制了鬼影,降低了误检率且使检测目标更加完整.
Abstract:
When ViBe algorithm is used to detect moving objects,the results of foreground extraction are prone to ghost,noise and incomplete detection results. To solve these problems,this paper proposes an improved ViBe algorithm. Firstly,the background model is initialized by using the median of multiframe images instead of single frame image; secondly,the dispersion coefficient is introduced to replace the original fixed distance determination threshold with the adaptive radius threshold; thirdly,the spatial consistency coefficient is introduced to construct the dynamic adaptive updating factor instead of the original fixed updating factor. The experimental results show that compared with the traditional ViBe algorithm and some improved ViBe algorithms,our improved ViBe algorithm can adapt to the dynamic background and illumination change,effectively suppress ghost,reduce the false detection rate and make the detection target more complete.

参考文献/References:

[1] 邱联奎,刘启亮,雷文龙. 基于背景减除与三帧差分相融合的运动检测[J]. 合肥工业大学学报(自然科学版),2014,37(5):572-577.
[2]BARRON J L,FLEET D J,BEAUCHEMIN S. Performance of optical flow techniques[J]. International journal of computer vision,1994,12(1):43-77.
[3]刘仲民,何胜皎,胡文瑾,等. 基于背景减除法的视频序列运动目标检测[J]. 计算机应用,2017,37(6):1777-1781.
[4]李清瑶,邹皓,赵群,等. 基于帧间差分自适应法的车辆抛洒物检测[J]. 长春理工大学学报(自然科学版),2018,41(4):108-113.
[5]李秋宇,张玉明,杨福猛,等. 一种视频微表情检测的改进光流算法[J]. 图学学报,2018,39(3):448-452.
[6]BHARTI,THIND T. Background subtraction techniques-review[J]. International journal of innovative technology & exploring engineering,2013,2(3):3099-3104.
[7]EVANGELIO R H,PATZOLD M,KELLER I,et al. Adaptively splitted gmm with feedback improvement for the task of background subtraction[J]. IEEE transactions on information forensics & security,2014,9(5):863-874.
[8]BARNICH O,VAN DROOGENBROECK M. ViBe:a universal background subtraction algorithm for video sequences[J]. IEEE transactions on image processing,2011,20(6):1709-1724.
[9]瞿中,刘帅,刘妍. 融合时域信息的自适应ViBe算法[J]. 计算机工程与设计,2019,40(3):189-194.
[10]杨丹,戴芳. 运动目标检测的ViBe算法改进[J]. 中国图象图形学报,2018,23(12):41-56.
[11]张磊,孟亮. 基于最小误差阈值自适应的ViBe改进算法[J]. 现代电子技术,2019,42(4):169-173.
[12]ZHAO W,WANG L,ZHANG Z. A novel atom search optimization for dispersion coefficient estimation in groundwater[J]. Future generation computer systems,2019,91(2):601-610.

备注/Memo

备注/Memo:
收稿日期:2020-07-08.
基金项目:玉林师范学院高层次人才科研启动基金项目(G2018015).
通讯作者:张钦礼,博士,教授,研究方向:计算机视觉.E-mail:zqlynu@163.com
更新日期/Last Update: 2020-11-15