动态背景下基于改进视觉背景提取的前景检测

陈星明; 廖娟; 李勃; 陈启美

doi:10.3788/OPE.20142209.2545

您当前的位置：

首页 >

文章列表页 >

动态背景下基于改进视觉背景提取的前景检测

信息科学 | 更新时间：2020-08-13

- 动态背景下基于改进视觉背景提取的前景检测
- Foreground detection based on modified ViBe in dynamic background
- 光学精密工程 2014年22卷第9期页码：2545-2552
- 作者机构：
  
  南京大学电子科学与工程学院,江苏南京,210046
- 作者简介：
- 基金信息：
  
  交通运输部科技项目（No.2012-364-641-209），国家自然科学基金资助项目（No.61105015），江苏省自然科学基金资助项目（No.BK2011511）
- DOI：10.3788/OPE.20142209.2545
  中图分类号： TP391.4
- 收稿日期：2014-01-17，
  
  修回日期：2014-03-18，
  
  纸质出版日期：2014
- 稿件说明：
移动端阅览
陈星明, 廖娟, 李勃等. 动态背景下基于改进视觉背景提取的前景检测[J]. 光学精密工程, 2014,22(9): 2545-2552

CHEN Xing-ming, LIAO Juan, LI Bo etc. Foreground detection based on modified ViBe in dynamic background[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2545-2552
陈星明, 廖娟, 李勃等. 动态背景下基于改进视觉背景提取的前景检测[J]. 光学精密工程, 2014,22(9): 2545-2552 DOI： 10.3788/OPE.20142209.2545.

CHEN Xing-ming, LIAO Juan, LI Bo etc. Foreground detection based on modified ViBe in dynamic background[J]. Editorial Office of Optics and Precision Engineering, 2014,22(9): 2545-2552 DOI： 10.3788/OPE.20142209.2545.

摘要

由于视觉背景提取算法（ViBe）对存在动态背景的户外视频的前景检测结果依然不够精确，故提出了一种改进的ViBe算法。文中描述了经典ViBe算法及其特点；介绍了改进的ViBe算法针对动态背景的改进措施。该算法采用多帧连续图像初始化背景模型，降低了单帧图像初始化所产生的鬼影"对前景检测精度的影响；在匹配过程中，引入自适应的匹配阈值，克服了单个的全局阈值对动态背景适应能力差的问题；最后，在更新过程引入空间一致性判断与模糊准则来减少算法的误检，提高了算法的鲁棒性。实验结果表明，该算法可以有效地检测动态背景下的运动目标，检测准确率比经典ViBe算法提高了20%以上。

Abstract

As Visual Background Extractor(ViBe) can not implement foreground detection precisely for a particular scene with dynamic backgrounds

This paper proposes a modified ViBe algorithm. It describes the original ViBe algorithm and its characteristics and discusses several modification schemes for the original ViBe in dynamic background scenes. Firstly

model initialization is conducted with several continuous frames instead of one single frame to handle ghosts. Then

self-adaptive threshold is adopted in the process of model matching so that background models is better suitable for the dynamic background. Finally

a spatial coherence estimation and a fuzzy rule in model maintenance are proposed to reduce false detections and to improve the robustness of the algorithm. Experiments demonstrate that the algorithm proposed detects effectively the movement targets in dynamic background scenes and its precision is improved by 20 percent as compared with that of the original ViBe algorithm.

关键词

Keywords

references

KERANER J K,THOMPSON W B,BOLEY D L. Optical flow estimation:an error analysis of gradient-based methods with local optimization[J].IEEE Transaction on Patten and Analysis Machine Intelligence, 1987, 9(2):229-244.

BRUTZER S, HOFERLIN B, HEIDEMANN G. Evaluation of background subtraction techniques for video surveillance[C]. Computer Vision and Pattern Recognition, 2011:1937-1944.

BOUWMANS T. Recent advanced statistical background modeling for foreground detection:a systematic survey[J]. Recent Patents on Computer Science, 2011, 4(3):146-176.

朱娟娟, 郭宝龙. 复杂场景中基于变块差分的运动目标检测[J]. 光学精密工程, 2011, 19(1):184-191. ZHU J J, GUO B L. Moving object detection based on variant block difference in complex scenes [J]. Opt. Precision Eng., 2011, 19(1):184-191.(in Chinese)

李刚, 曾锐利, 林凌, 等. 基于帧间颜色梯度的背景建模[J]. 光学精密工程, 2007, 15(8):1258-1262. LI G, ZENG R L, LIN L, et al.. A novel background modeling method based on color grade of different frames [J]. Opt.Precision Eng., 2007, 15(8):1258-1262.(in Chinese)

张红颖, 胡正. CenSurE 特征和时空信息相结合的运动目标检测[J]. 光学精密工程, 2013, 21(9):2453-2463. ZHANG H Y, HU ZH. Moving object detection in combination of CenSurE and spatial-temporal information [J]. Opt. Precision Eng., 2013, 21(9):2453-2463. (in Chinese)

STAUFFER C, GRIMSON W E L. Learning patterns of activity using real-time tracking [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(8):747-757.

ZIVKOVIC Z, VAN D H F. Efficient adaptive density estimation per image pixel for the task of background subtraction [J]. Pattern Recognition Letters, 2006:773-780.

WREN C R, AZARBAYEJANI A, DARRELL T, et al.. Pfinder:Real-time tracking of the human body [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1997, 19(7):780-785.

MADDALENA L, PETROSINO A. A self-organizing approach to background subtraction for visual surveillance applications [J]. IEEE Transactions on Image Processing, 2008, 17(7):1168-1177.

MADDALENA L, PETROSINO A. A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection[J]. Neural Computer Application, 2010, 19(2):179-186.

MADDALENA L, PETROSINO A. The SOBS algorithm:what are the Limits?[C]. Computer Vision and Pattern Recognition Workshops, 2012:21-26.

BARNICH O, DROOGENBROECK M V. ViBe:A universal background subtraction algorithm for video sequences [J]. IEEE Transaction on Image Processing, 2011, 20(6):1709-1724.

DROOGENBROECK M V, PAQUOT O. Background subtraction:experiments and improvements for ViBe [C]. Computer Vision and Pattern Recognition Workshops, 2012:32-37.

DING J, MA R, CHEN S. A scale-based connected coherence tree algorithm for image segmentation [J]. IEEE Transaction on Image Process, 2008, 17(2):204-216.

浏览量

153

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于元胞自动机的动态背景运动目标检测

张量低秩表示和时空稀疏分解的视频前景检测

CenSurE特征和时空信息相结合的运动目标检测

SIFT特征匹配和差分相乘融合的运动目标检测