基于三维高斯混合码本模型的运动目标检测算法

黄进; 金炜东; 秦娜

doi:10.3969/j.issn.0258-2724.2012.04.020

基于三维高斯混合码本模型的运动目标检测算法

doi: 10.3969/j.issn.0258-2724.2012.04.020

基金项目:

国家自然科学基金重点项目(61134002)

中央高校基本科研业务费专项资金资助项目(SWJTU09BR069)

计量
- 文章访问数: 993
- HTML全文浏览量: 68
- PDF下载量: 757
- 被引次数: 0
出版历程
- 收稿日期: 2011-11-03
- 刊出日期: 2012-08-25

Moving Objects Detection Algorithm Based on Three-Dimensional Gaussian Mixture Codebook Model

摘要

摘要: 为解决智能视觉监控中码本模型参数调节困难和高斯混合模型概率分布计算的复杂性,提出了一种基于三维高斯混合码本模型的运动目标检测算法.该算法基于RGB空间建立码本模型,然后基于码字中的R、G、B 分量建立三维高斯模型,从而使整个码本具有三维高斯混合模型的特征.实验结果表明:该算法具有较高的实时性(该算法的平均帧率约23.0帧/s,而iGMM(improved Gaussian mixture model)算法约9.0帧/s,BM(Bayes model)算法约6.2帧/s,CBM(codebook model)算法约10.7帧/s),且具有良好的检测质量.
- 目标检测 /
- 码本 /
- 高斯混合
Abstract: In order to solve the difficulty of adjusting parameters for the codebook model and the computational complexity of probability distribution for the Gaussian mixture model in intelligent visual surveillance, a moving objects detection algorithm based on the three-dimensional Gaussian mixture codebook model was proposed. In this algorithm a codebook model based on RGB space is built, and then a three-dimensional Gaussian model based on R, G and B components in codewords is established. In this way, the characteristic of the three-dimensional Gaussian mixture model for the codebook model can be obtained. The experimental results show that the average frame rate of the proposed algorithm is about 23.0 frames per second, while it is about 9.0 frames per second for the iGMM (improved Gaussian mixture model) algorithm, about 6.2 frames per second for the BM (Bayes model) algorithm, and about 10.7 frames per second for CBM (codebook model) algorithm in the comparative experiments. Furthermore, the proposed algorithm can obtain a good detection quantity.
- object detection /
- codebook /
- Gaussian mixture

HTML全文

参考文献(19)

MA G, PARK S B, IOFFE A, et al. A real time object detection approach applied to reliable pedestrian detection//Proceedings of IEEE Intelligent Vehicles Symposium. Istanbul: IEEE Press, 2007: 755-760.

STRINGA E, REGAZZONI C S. Real-time video-shot detection for scene surveillance applications[J]. IEEE Transactions on Image Processing, 2000, 9(1): 69-79.

KARMANN K P, VON BRANDT A. Moving object recognition using an adaptive background memory//Proceedings of Time-varying Image Processing and Moving Object Recognition. Amsterdam: Elsevier Press, 1990: 289-296.

CUTLER R, DAVIS L. View-based detection and analysis of periodic motion//Proceedings of Fourteenth International Conference on Pattern Recognition. Brisbane: IEEE Press, 1998: 495-500.

TOYAMA K, KRUMM J, BRUMITT B, et al. Wallflower: Principles and practice of background maintenance//Proceedings of International Conference on Computer Vision 1999-Volume 1. Kerkyra: IEEE Computer Society, 1999: 255-261.

HARITAOGLU I, HARWOOD D, DAVIS L S. W4: Who? when? where? what? a real time system for detecting and tracking people//Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition. Grenoble: IEEE Press, 1998: 222-227.

ELGAMMAL A, HARWOOD D, DAVIS L. Non-parametric model for background subtraction[J]. Lecture Notes in Computer Science, 2000, 1843: 751-767.

HORPRASERT T, HARWOOD D, DAVIS L S. A statistical approach for real-time robust background subtraction and shadow detection//Proceedings of IEEE ICCV'99 Frame-Rate Workshop. Kerkyra: IEEE Computer Society, 1999: 1-19.

STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking// Conference on Computer Vision and Pattern Recognition. Fort Collins: IEEE Computer Society, 1999: 246-252.

KAEWTRAKULPONG P, BOWDEN R. An improved adaptive background mixture model for real-time tracking with shadow detection//Proceedings of 2nd European Workshp on Advanced Video-Based Surveillance Systems. London: Kluwer Academic Publishers, 2001: 149-158.

ZHANG J, CHEN C H. Moving objects detection and segmentation in dynamic video backgrounds//Proceedings of IEEE Conference on Technologies for Homeland Security. Woburn: IEEE Press, 2007: 64-69.

ZENG H C, LAI S H. Adaptive foreground object extraction for real-time video surveillance with lighting variations//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. Honolulu: IEEE Press, 2007: 1201-1204.

SUO P, WANG Y. An improved adaptive background modeling algorithm based on Gaussian mixture model//Proceedings of 9th International Conference on Signal Processing. Beijing: IEEE Press, 2008: 1436-1439.

LI L, HUANG W, GU I Y H, et al. Foreground object detection from videos containing complex background//Proceedings of eleventh ACM international conference on Multimedia. New York: ACM Press, 2003: 2-10.

KIM K, CHALIDABHONGSE T H, HARWOOD D, et al. Real-time foreground-background segmentation using codebook model[J]. Real-Time Imaging, 2005, 11(3): 172-185.

徐成,田峥,李仁发. 一种基于改进码本模型的快速运动检测算法[J]. 计算机研究与发展,2010,47(12): 2149-2156. XU Cheng, TIAN Zheng, LI Renfa. A fast motion detection method based on improved codebook model[J]. Journal of Computer Research and Development, 2010, 47(12): 2149-2156.

DOSHI A, TRIVEDI M. Hybrid cone-cylinder codebook model for foreground detection with shadow and highlight suppression//Proceedings of IEEE International Conference on Video and Signal Based Surveillance. Sydney: IEEE Press, 2006: 19-19.

LI Y, CHEN F, XU W, et al. Gaussian-based codebook model for video background subtraction[J]. Lecture Notes in Computer Science, 2006, 4222: 762-765.

郭烈,高龙,赵宗艳. 基于车载视觉的行人检测与跟踪方法[J]. 西南交通大学学报,2012,47(1): 19-25. GUO Lie, GAO Long, ZHAO Zongyan. Pedestrian detection and tracking based on automotive vision[J]. Journal of Southwest Jiaotong University, 2012, 47(1): 19-25.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 993
HTML全文浏览量: 68
PDF下载量: 757
被引次数: 0

基于三维高斯混合码本模型的运动目标检测算法

doi: 10.3969/j.issn.0258-2724.2012.04.020

计量

出版历程

Moving Objects Detection Algorithm Based on Three-Dimensional Gaussian Mixture Codebook Model

计量

出版历程

目录