基于混合高斯模型与码本算法的前景目标检测

doi:10.3969/j.issn.1000-3428.2012.05.001

计算机工程 ›› 2012, Vol. 38 ›› Issue (5): 1-4. doi: 10.3969/j.issn.1000-3428.2012.05.001

• 专栏 • 下一篇

基于混合高斯模型与码本算法的前景目标检测

叶勇，管业鹏，李晶晶

(上海大学通信与信息工程学院，上海 200072)

收稿日期:2011-09-13 出版日期:2012-03-05 发布日期:2012-03-05
作者简介:叶勇(1986－)，男，硕士研究生，主研方向：数字图像处理，运动目标检测；管业鹏，教授、博士生导师；李晶晶，硕士研究生
基金资助:
国家自然科学基金资助项目(60872117)；上海大学创新基金资助项目(SHUCX112121)

Foreground Target Detection Based on Gaussian Mixture Model and Codebook Algorithm

YE Yong, GUAN Ye-peng, LI Jing-jing

(School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China)

Received:2011-09-13 Online:2012-03-05 Published:2012-03-05

摘要/Abstract

摘要：

提出一种基于混合高斯模型(GMM)与码本算法的前景目标检测方法。利用GMM进行背景图像建模并初步提取前景对象，对背景图像进行码本学习，将码本建模得到的前景对象与GMM得到的前景对象相融合，根据前后2次帧间差分得到前景对象的比例关系，自适应地更新高斯参数和扩展码字，得到前景对象目标。实验结果表明，该方法实时性好，可消除视频序列中的阴影和鬼影，提取完整的前景对象。

关键词: 前景检测, 阴影消除, 混合高斯模型, 码本算法, 帧间差分

Abstract:

This paper proposes a foreground moving object detection method based on Gaussian Mixture Model(GMM) and codebook. It uses GMM to extract initial foreground object, learns the background in use of codebook. It associates the foreground object obtained by GMM with the object of codebook foreground, updates the parameters of Gaussian model and codebook adaptively, according to the ratio between the foreground in 2 adjacent frames, and gets the moving object. Experimental results show that the method can eliminate the shadow of the video sequence and ghosting effectively, as well as obtain the entire foreground object in real time.

Key words: foreground detection, shadow elimination, Gaussian Mixture Model(GMM), codebook algorithm, inter-frame difference

中图分类号:

TP39

叶勇, 管业鹏, 李晶晶. 基于混合高斯模型与码本算法的前景目标检测[J]. 计算机工程, 2012, 38(5): 1-4.

XIE Yong, GUAN Ye-Feng, LI Jing-Jing. Foreground Target Detection Based on Gaussian Mixture Model and Codebook Algorithm[J]. Computer Engineering, 2012, 38(5): 1-4.

http://www.ecice06.com/CN/Y2012/V38/I5/1

参考文献

[1] 孙吉花. 背景减除的算法研究[D]. 长沙: 国防科学技术大学, 2006.
[2] Chen Yuting, Chen Chusong. Huang Chunrong. Efficient Hier- archical Method for Background Subtraction[J]. Pattern Recogni-

tion, 2007, 40(10): 2706-2715.
[3] Wren C R, Azarbayejani A, Darrell T, et al. Real-time Tracking of the Human Body[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(10): 780-785.
[4] Stauffer C, Grimson W E L. Adaptive Background Mixture Models for Real-time Tracking[C]//Proceedings of Conference on Computer Vision and Pattern Recognition. Fort Collins, USA: IEEE Computer Society, 1999.
[5] Stauffer C, Grimson W E L. Learning Patterns of Activity Using Real-time Tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757.
[6] Song Xuehua, Chen Jingzhu. A Robust Moving Objects Detection Based on Improved Gaussian Mixture Model[C]//Proceedings of International Conference on Artificial Intelligence and Computa- tional Intelligence. [S. l.]: IEEE Press, 2010.
[7] Wang Yanjiang. An Improved Adaptive Background Modeling Algorithm Based on Gaussian Mixture Model[C]//Proceedings of International Conference on Signal Processing. [S. l.]: IEEE Press, 2009.
[8] Luo Jinmian, Zhu Juan. Adaptive Gaussian Mixture Model Based on Feedback Mechanism[C]//Proceedings of International Conference on Computer Design and Applications. Chengdu, China: [s. n.], 2010.
[9] Kim K, Chalidabhongse T, Harwood D, et al. Real-time Fore- ground-background Segmentation Using Codebook Model[J]. Real-time Imaging, 2005, 11(3): 167-256.
[10] Pal A, Schaefer G, Celebi M E. Robust Codebood-based Video Background Subtraction[C]//Proceedings of International Confer- ence on Acoustics Speech and Signal Processing. Dallas, USA: IEEE Press, 2010.
[11] Sigari M H, Fathy M. Real-time Background Modeling/Subtraction Using Tow-layer Codebook Model[C]//Proceedings of Interna- tional Multi-conference on Engineers and Computer Scientists. Hong Kong, China: [s. n.], 2008.
[12] Perera A G A, Brooksby G, Hoogs A, et al. Moving Object Segmentation Using Scene Understanding[C]//Proceedings of Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE Press, 2006.
[13] 王明吉, 肖桂丹. 抗干扰的运动目标检测算法[J]. 计算机工程, 2010, 36(3): 232-233.
[14] Mingli S, Wang Huiqiong. Gaussian Mixture Model Based Approach on Color Transfer[J]. Journal of Computer-aided Design and Computer Graphics, 2008, 20(11): 1471-1476.
[15] 刘鑫, 刘辉, 强振平, 等. 混合高斯模型和帧间差分相融合的自适应背景模型[J]. 中国图象图形学报, 2008, 13(4): 729- 734.
[16] Lee D S. Effective Gaussian Mixture Learning for Video Background Subtraction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(5): 827-832.
[17] Computer Vision and Robotics Research Laboratory. Groud- truth[EB/OL]. (2007-10-12). http://cvrr.uscd.edu/aton/shadow.

选择文件类型/文献管理软件名称

选择包含的内容

基于混合高斯模型与码本算法的前景目标检测

Foreground Target Detection Based on Gaussian Mixture Model and Codebook Algorithm

PDF

可视化

被引次数

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

本文评价

[1]	张国庭, 陈利霞, 周泽锋. 结合l_1/2范数与显著性约束的背景减除[J]. 计算机工程, 2022, 48(6): 263-269.
[2]	张显炀, 朱晓宇, 林浩申, 刘刚, 安喜彬. 基于高斯混合-变分自编码器的轨迹预测算法[J]. 计算机工程, 2020, 46(7): 50-57.
[3]	柳长源,曹园园,罗一鸣. 基于视频图像的车辆实时检测系统[J]. 计算机工程, 2019, 45(2): 265-269,277.
[4]	陈晓春, 林博溢, 孙乾, 张坤华. 基于运动区域差分与卷积神经网络的动作识别[J]. 计算机工程, 2019, 45(12): 274-280,293.
[5]	张勇,袁家政,刘宏哲,李青. 基于结构张量的GrabCut图像分割算法[J]. 计算机工程, 2017, 43(8): 258-265,271.
[6]	段锁林,严翔,朱方,史兵. 基于改进混合高斯模型与六帧差分的目标检测算法[J]. 计算机工程, 2017, 43(7): 234-238.
[7]	陆星家,王玉金,陈志荣,林勇. 基于隐SVM和混合高斯模型的目标检测算法[J]. 计算机工程, 2016, 42(6): 287-292.
[8]	王思明，赵伟. 亮度特征自相关和GMM相结合的目标检测[J]. 计算机工程, 2014, 40(5): 219-223.
[9]	喻旭勇，王直杰. 基于灰度触发的Mean Shift自动跟踪算法[J]. 计算机工程, 2014, 40(1): 228-231,235.
[10]	韩劲松. 基于自适应GMM的X射线图像智能检测[J]. 计算机工程, 2012, 38(5): 205-207.
[11]	李科伟, 杨晓敏, 何小海, 张生军. 基于弱阈值分割的运动人体阴影去除算法[J]. 计算机工程, 2012, 38(5): 173-175.
[12]	朱建武, 李榕, 凌云. 基于FPGA的目标跟踪系统设计与实现[J]. 计算机工程, 2012, 38(5): 243-246.
[13]	孙毅刚, 李鸿, 张红颖. 基于改进混合高斯模型的运动目标检测算法[J]. 计算机工程, 2012, 38(18): 166-170.
[14]	郝毫刚, 陈家琪. 基于五帧差分和背景差分的运动目标检测算法[J]. 计算机工程, 2012, 38(04): 146-148.
[15]	丁芒, 彭黎辉, 张煦, 刘强, 姚丹亚. 复杂交通场景中的运动目标提取方法[J]. 计算机工程, 2011, 37(7): 184-186.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于混合高斯模型与码本算法的前景目标检测

Foreground Target Detection Based on Gaussian Mixture Model and Codebook Algorithm

PDF

可视化

被引次数

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

本文评价