| 360 | 19 | 103 |
| 下载次数 | 被引频次 | 阅读次数 |
针对经典Vibe算法在运动目标检测时存在鬼影、阴影和噪声干扰的问题,提出了一种融合混合高斯模型的改进的Vibe算法。在背景初始化阶段,采用五帧差分算法与八邻域的像素值填充获得的真实背景并且消除鬼影现象;通过混合高斯模型权值与Vibe随机取样概率相结合进行背景更新,将得到的运动目标进行形态学处理,使运动目标更加清晰;最后,在YCb Cr颜色空间进行阴影消除。实验结果表明,改进后的Vibe算法不仅能够有效地去除鬼影,并且在消除阴影与噪声方面取得了良好的效果。
Abstract：To solve the problems of the classical Vibe algorithm,such as ghost,shadow and noise interference in moving object detection,an improved Vibe algorithm which combines Gaussian mixture model was put forward.Firstly,by using five frame difference algorithm and eight-neighbor pixel value to fill in the background initialization phase,the true background is obtained and the ghosting phenomenon is eliminated.Then the background is updated by combining the Gaussian mixture model and Vibe random sampling probability,the moving targets are clearer with morphological method.And the shadow is eliminated in the YCbCr color space.The test results show that the improved Vibe algorithm not only can effectively eliminate the ghost image,but also has good effect in eliminating the shadow and noise.
[1]CHIU C C,KU M Y,LIANG L W.A robust object segmentation system using a probability based background extraction algorithm[J].IEEE Transactions on Circuits and Systems for Video Technology,2010,20(4):518-528.
[2]GOYETTE N,JODOIN P M,PORIKLI F,et al.Change detection.net:A new change detection benchmark dataset[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.Providence:IEEE,2012:1-8.
[3]张玲,陈丽敏,何伟,等.基于视频的改进帧差法在车流量检测中的应用[J].重庆大学学报,2004,27(5):31-33.
[4]BARNICH O,VAN DROOGENBROCCK M.Vi Be:A universal background subtraction algorithm for video seq-uences[J].IEEE Transactions on Image Processing,2011,20(6):1709-1724.
[5]胡小冉,孙涵.一种新的基于Vibe的运动目标检测方法[J].计算机科学,2014,41(2):149-152.
[6]邓亚丽,毋立芳,李云腾.一种有效的图像阴影自动去除算法[J].信号处理,2011,27(11):1725-1728.
[7]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray scale and rotation invariant texture analysis with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[8]ZIVKOVIC Z.Improved adaptive Gaussian mixture model for background subtraction[C]∥Proceedings of the 17th International Conference on Pattern Recognition.IEEE,2004:28-31.
[9]杨勇,孙明伟,金裕成.一种改进视觉背景提取(Vibe)算法的车辆检测方法[J].重庆邮电大学学报(自然科学版),2014,26(3):397-403.
[10]卢清华,吴志伟,范彦斌,等.基于混合高斯模型的运动车辆检测方法[J].光电子·激光,2013,24(4):751-757.
[11]李鸿.基于混合高斯模型的运动检测及阴影消除算法研究[D].天津:中国民航大学,2013.
[12]房正华.基于视频图像的车辆阴影检测方法研究[D].青岛:中国海洋大学,2007.
[13]甘玲,赵华翔.一种改进的Vi Be算法结合多特征融合的阴影移除方法[J].微电子学与计算机,2015,32(11):152-157.
[14]SANIN A,SANDERSON C,LOVELL B C.Improved shadow removal for robust person tracking in surveillance scenarios[C]∥Proceeding of the 20th International Conference on Pattern Recognition.IEEE,2010:141-144.
[15]LI Y Q,CHEN W Z,JIANG R.The integration adjacent frame difference of improved Vi Be for foreground object detection[C]∥The 7th International Conference on Wi COM.Piscataway:IEEE,2011:1-4.
[16]徐久强,江萍萍,朱宏博,等.面向运动目标检测的Vi Be算法改进[J].东北大学学报(自然科学版),2015,36(9):12271231.
[17]DROOGENBROECK M V,PAQUOT O.Background subtraction:Experiments and improvements for Vi Be[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Providence:IEEE,2012:32-37.
[18]JENIFA R A T,AMALI J R,AKILA C,KAYITHA V.Rapid background subtraction from video sequences[C]∥IEEE International Conference on Computing,Electronics and Electrical Technologies.Kumaracoil:IEEE,2012:1077-1086.
[19]HEIKKILA M,PIETIKAINEN M,SCHMID C.Description of interest regions with local binary patterns[J].Pattern Recognition,2009,42(3):425-436.
[20]XIA Y Q,NING S H,SHEN H.Moving targets detection algorithm based on background subtraction and frames subtraction[C]∥IEEE International Conference on Industrial Mechatronics and Automation.Wuhan:IEEE,2010:122-125.
基本信息:
DOI：10.16152/j.cnki.xdxbzr.2017-03-008
中图分类号:TP391.41
引用信息:
[1]张红瑞,马永杰.融合混合高斯模型的改进的Vibe算法[J].西北大学学报(自然科学版),2017,47(03):361-366.DOI:10.16152/j.cnki.xdxbzr.2017-03-008.
基金信息:
国家自然科学基金资助项目(41461078)
2017-06-25
2017-06-25