摘要
针对ViBe算法采用第一帧初始化背景模型没有考虑像素值在时域上变化的情况,提出一种融合时域信息的自适应ViBe算法。提出一个历史像素值队列反映像素值在时域上的变化情况;提出一种结合自适应思想的阈值分割方法对前景像素和背景像素进行分割,使ViBe算法适应场景中不同动态区域;提出一种自适应的更新因子,通过自适应更新机制使背景模型能够在不同背景下更加可靠。实验结果表明,改进后的ViBe算法能够快速适应动态背景,使检测结果更为准确。
The initialization of background model in the first frame neglects the pixel values changes in the time domain,to solve the problem,a self-adaptive ViBe algorithm with time domain information was proposed.A historical pixel value queue to reflect the pixel changes in the time domain was proposed.A segmentation method based on the self-adaptive idea was proposed,which ensured ViBe adapting to different dynamic regions in scene.A self-adaptive updating factor was proposed,which made the background model reliable in different backgrounds.Experimental results show that the improved algorithm can quickly adapt to the dynamic background and make the detection results more accurate.
引文
[1]Zhuang X,Kang W,Wu Q,et al.Real-time vehicle detection with foreground-based cascade classifier[J].IET Image Processing,2016,10(4):289-296.
[2]DING Jie,KUANG Liqun,HAN Xie.Improved moving object detection method based on ViBe[J].Computer Engineering&Design,2017,38(2):374-378(in Chinese).[丁洁,况立群,韩燮.基于ViBe的运动目标检测改进方法[J].计算机工程与设计,2017,38(2):374-378.]
[3]Shahbaz A,Hariyono J,Jo K H.Evaluation of background subtraction algorithms for video surveillance[C]//Frontiers of Computer Vision.IEEE,2015:1-4.
[4]Singla N.Motion detection based on frame difference method[J].International Journal of Information&Computation Technology,2014,4(15):1559-1565.
[5]Liu X,Zhao G,Yao J,et al.Background subtraction based on low-rank and structured sparse decomposition[J].IEEETransactions on Image Processing,2015,24(8):2502-2514.
[6]Evangelio R H,Patzold M,Keller I,et al.Adaptively splitted GMM with feedback improvement for the task of background subtraction[J].IEEE Transactions on Information Forensics&Security,2014,9(5):863-874.
[7]Chen X M,Liao J,Bo L I,et al.Foreground detection based on modified ViBe in dynamic background[J].Optics&Precision Engineering,2014,22(9):2545-2552.
[8]Zhu Z,Cheng C,Yao Z.Multi-scale based enhanced ViBe for background modeling[J].Journal of Beijing Jiaotong University,2015,39(2):1-6.
[9]Kryjak T,Komorkiewicz M,Gorgon M.Real-time foreground object detection combining the pbas background modelling algorithm and feedback from scene analysis module[J].International Journal of Electronics&Telecommunications,2014,60(1):53-64.
[10]Wang Y,Jodoin P M,Porikli F,et al.CDnet 2014:An expanded change detection benchmark dataset[C]//IEEE Conference on Computer Vision and Pattern Recognition Workshops.IEEE Computer Society,2014:393-400.
[11]Shah M,Deng J D,Woodford B J,et al.A self-adaptive CodeBook(SACB)model for real-time background subtraction[J].Image and Vision Computing,2015,38:52-64.
[12]AN Shiquan,LIAO Chunmei,QU Zhong.Adaptive Codebook model algorithm by illumination change prediction[J].Computer Engineering&Design,2017,38(8):2194-2198(in Chinese).[安世全,廖春梅,瞿中.光照改变预测的自适应码本模型算法[J].计算机工程与设计,2017,38(8):2194-2198.]