基于视觉背景提取的自适应运动目标提取算法

doi:10.11772/j.issn.1001-9081.2015.07.2029

计算机应用 ›› 2015, Vol. 35 ›› Issue (7): 2029-2032.DOI: 10.11772/j.issn.1001-9081.2015.07.2029

基于视觉背景提取的自适应运动目标提取算法

吕嘉卿, 刘立程, 郝禄国, 张文忠

广东工业大学信息工程学院, 广州 510006

收稿日期:2015-02-02 修回日期:2015-03-26 发布日期:2015-07-17 出版日期:2015-07-10
通讯作者: 吕嘉卿(1991-),女,广东顺德人,硕士研究生,主要研究方向:视频图像处理,katenan@126.com
作者简介:刘立程(1972-),男,福建上杭人,副教授,博士,主要研究方向:无线通信、数字信号处理; 郝禄国(1968-),男,河北霸县人,讲师,博士,主要研究方向:多媒体通信、数字信号处理; 张文忠(1991-),男,广东汕头人,硕士研究生,主要研究方向:信号与信息系统。

Adaptive moving object extraction algorithm based on visual background extractor

LYU Jiaqing, LIU Licheng, HAO Luguo, ZHANG Wenzhong

College of Information Engineering, Guangdong University of Technology, Guangzhou Guangdong 510006, China

Received:2015-02-02 Revised:2015-03-26 Online:2015-07-17 Published:2015-07-10

摘要/Abstract

摘要：

在复杂场景下的视频运动目标提取是视频分析技术的首要工作。为了解决前景运动目标提取的精确度不高的问题,提出一种基于视觉背景提取(ViBE)的改进视频运动目标提取算法(ViBE⁺)。首先,在背景模型初始化阶段采用像素的菱形邻域来简化样本信息;其次,在前景运动目标提取阶段引入自适应分割阈值来适应场景的动态变化;最后,在更新阶段提出背景重建和调整更新因子方法来处理光照变化的情形。实验结果表明,对于复杂视频场景LightSwitch的运动目标提取结果在相似度指标上,改进后的算法与混合高斯模型(GMM)算法、码本模型算法以及原始ViBE算法相比,分别提高了1.3倍、1.9倍以及3.8倍。所提算法能够在有效时间内对复杂场景具有较好的自适应性,且性能明显优于对比算法。

关键词: 前景提取, 视觉背景提取, 背景建模, 自适应阈值, 更新因子

Abstract:

The prior work of video analysis technology is video foreground detection in complex scenes. In order to solve the problem of low accuracy in foreground moving target detection, an improved moving object extraction algorithm for video based on Visual Background Extractor (ViBE), called ViBE⁺, was proposed. Firstly, in the model initialization stage, each background pixel was modeled by a collection of its diamond neighborhood to simply the sample information. Secondly, in the moving object extraction stage, the segmentation threshold was adaptively obtained to extract moving object in dynamic scenes. Finally, for the sudden illumination change, a method of background rebuilding and update-parameter adjusting was proposed during the process of background update. The experimental results show that, compared with the Gaussian Mixture Model (GMM) algorithm, Codebook algorithm and original ViBE algorithm, the improved algorithm's similarity metric on moving object extracting results increases by 1.3 times, 1.9 times and 3.8 times respectively in complex video scene LightSwitch. The proposed algorithm has a better adaptability to complex scenes and performance compared to other algorithms.

Key words: foreground extraction, Visual Background Extractor (ViBE), background modeling, self-adaptive threshold, update-parameter

中图分类号:

TP391.413

吕嘉卿, 刘立程, 郝禄国, 张文忠. 基于视觉背景提取的自适应运动目标提取算法[J]. 计算机应用, 2015, 35(7): 2029-2032.

LYU Jiaqing, LIU Licheng, HAO Luguo, ZHANG Wenzhong. Adaptive moving object extraction algorithm based on visual background extractor[J]. Journal of Computer Applications, 2015, 35(7): 2029-2032.

参考文献

[1] SHEN J, YANG W, LU Z, et al. Information integration for accurate foreground segmentation in complex scenes [J]. IET Image Processing, 2012, 6(5): 596-605.
[2] KUMAR A, TUNG F, WONG A, et al. A decoupled approach to illumination-robust optical flow estimation [J]. IEEE Transactions on Image Processing, 2013, 22(10): 4136-4147.
[3] LI B, YANG G. Adaptive foreground detection approach of Gaussian mixture mode [J]. Journal of Image and Graphics, 2013, 18(12): 1620-1627.(李百惠,杨庚.混合高斯模型的自适应前景提取[J].中国图象图形学报,2013,18(12):1620-1627.)
[4] STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking [C]// CVPR 1999: Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 1999: 246-252.
[5] ZIVKOVIC Z. Improved adaptive Gaussian mixture model for background subtraction [C]// ICPR 2004: Proceedings of the 17th International Conference on Pattern Recognition. Piscataway: IEEE, 2004: 28-31.
[6] KYUNGNAM K, CHALIDABHONGSE T H, HARWOOD D, et al. Background modeling and subtraction by codebook construction [C]// Proceedings of the 2004 International Conference on Image Processing. Piscataway: IEEE, 2004: 3061-3064.
[7] LIU H, HOU X, HAO X, et al. Moving object detection algorithm based random sample model [J]. Journal of Electronic Measurement and Instrument, 2013, 27(12): 1155-1161.(刘红海,侯向华,郝秀兰,等.采用随机样本进行运动目标检测的算法研究[J].电子测量与仪器学报,2013,27(12):1155-1161.)
[8] YU Y, CAO M, YUE F. EViBE: an improved ViBE algorithm for detecting moving objects [J]. Chinese Journal of Scientific Instrument, 2014, 35(4): 924-931.(余烨,曹明伟,岳峰.EViBE:一种改进的ViBE运动目标检测算法[J].仪器仪表学报,2014,35(4):924-931.)
[9] van DROOGENBROECK M, PAQUOT O. Background subtraction: experiments and improvements for ViBE [C]// CVPRW 2012: Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2012: 32-37.
[10] GE W, DONG Y, GUO Z, et al. Background Subtraction with dynamic noise sampling and complementary learning [C]// ICPR 2014: Proceedings of the 22nd International Conference on Pattern Recognition. Piscataway: IEEE, 2014: 2341-2346.
[11] SU Y, LI A, JIANG K, et al. Improved visual background extractor model for moving objects detecting algorithm [J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(2): 232-240.(苏延召,李艾华,姜柯,等.改进视觉背景提取模型的运动目标检测算法[J].计算机辅助设计与图形学学报,2014,26(2):232-240.)
[12] BARNICH O, van DROOGENBROECK M. ViBE: a powerful random technique to estimate the background in video sequences [C]// ICASSP 2009: Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2009: 945-948.
[13] 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.
[14] FISHER R B. Change detection in color images [EB/OL]. [2014-12-18]. http://homepages.inf.ed.ac.uk/rbf/PAPERS/iccv99.pdf.
[15] TOYAMA K, KRUMM J, BRUMITT B, et al. Wallflower: principles and practice of background maintenance [C]// Proceedings of the 7th IEEE International Conference on Computer Vision. Piscataway: IEEE, 1999: 255-261.
[16] GOYETTE N, JODOIN P, PORIKLI F, et al. Changedetection.net: a new change detection benchmark dataset [C]// CVPRW 2012: Proceedings of the 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2012: 1-8.
[17] AGARWAL S, AWAN A, ROTH D. Learning to detect objects in images via a sparse, part-based representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(11): 1475-1490.

基于视觉背景提取的自适应运动目标提取算法

Adaptive moving object extraction algorithm based on visual background extractor

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	汪鹏, 张大蔚, 陆正军, 李林昊. 基于可靠性低秩因子分解和泛化差异性差分的运动目标检测[J]. 《计算机应用》唯一官方网站, 2023, 43(2): 514-520.
[2]	王思鹏, 杜昌平, 叶志贤, 宋广华, 郑耀. 基于多步神经网络观测器的扑翼飞行器缓变故障检测[J]. 计算机应用, 2020, 40(8): 2449-2454.
[3]	张皓然, 王学渊, 李小霞. 基于自适应阈值活动语音检测和最小均方误差对数谱幅度估计的低信噪比降噪算法[J]. 计算机应用, 2020, 40(6): 1763-1768.
[4]	王忠锋, 徐志远, 宋纯贺, 张宏宇, 蔡颖凯. 基于梯度的深度网络剪枝算法[J]. 计算机应用, 2020, 40(5): 1253-1259.
[5]	王治忠, 李泓毅, 韩闯. 基于香农能量与自适应阈值的心电QRS复合波检测算法[J]. 计算机应用, 2020, 40(1): 304-310.
[6]	丁莲静, 刘光帅, 李旭瑞, 陈晓文. 加权信息熵与增强局部二值模式结合的人脸识别[J]. 计算机应用, 2019, 39(8): 2210-2216.
[7]	杜启亮, 黎浩正, 田联房. 基于Adaboost和码本模型的手扶电梯出入口视频监控方法[J]. 计算机应用, 2017, 37(9): 2610-2616.
[8]	彭政, 陈东方, 王晓峰. 正则化超分辨率重建过程的自适应阈值去噪[J]. 计算机应用, 2017, 37(7): 2084-2088.
[9]	杨婷, 李博, 石雯婧, 张成飞. 基于DSP的单车道车流量实时监测算法[J]. 计算机应用, 2017, 37(2): 593-596.
[10]	陈凯星, 刘赟, 王金海, 袁玉波. 基于遗传机制和高斯变差的自动前景提取方法[J]. 计算机应用, 2017, 37(11): 3231-3237.
[11]	黄泳航, 汤庸, 李春英, 汤志康, 刘继伟. 基于社区划分的学术论文推荐模型[J]. 计算机应用, 2016, 36(5): 1279-1283.
[12]	谢瑞, 李钢, 张仁斌. 液晶显示器斑痕缺陷高质量背景建模[J]. 计算机应用, 2016, 36(4): 1151-1155.
[13]	兰丽, 何小海, 吴晓红, 滕奇志. 基于超像素和局部颜色恒常性的自适应阴影去除[J]. 计算机应用, 2016, 36(10): 2837-2841.
[14]	吕笃良, 贾振红, 杨杰, Nikola KASABOV. 基于非下采样剪切波变换与引导滤波结合的遥感图像增强[J]. 计算机应用, 2016, 36(10): 2880-2884.
[15]	李春英, 汤庸, 汤志康, 黄泳航, 袁成哲, 赵剑冬. 面向大规模学术社交网络的社区发现模型[J]. 计算机应用, 2015, 35(9): 2565-2568.