计算机科学 ›› 2015, Vol. 42 ›› Issue (Z6): 154-157.
王辉,宋建新
WANG Hui and SONG Jian-xin
摘要: Vibe算法是一种高效的像素级背景建模算法。该算法在运动目标检测过程中无法快速抑制鬼影,同时不能根据前景运动快慢调整背景更新速度。针对这些问题,提出了一种基于阈值的自适应Vibe目标检测算法。当某像素点被Vibe模型判别为前景时,采用Otsu算法计算图像的分割阈值。根据阈值对该像素点进行再次判别抑制鬼影像素点,并重新初始化该像素点的背景模型。通过计算运动目标的质心差,改进的Vibe算法能够自适应地调整背景的更新速度。结果表明,与原Vibe算法相比,改进后的算法能够在更少的帧数内有效地抑制鬼影,更加准确地检测出前景目标。
[1] 张磊,傅志中,周岳平.基于HSV颜色空间和Vibe算法的运动目标检测[J].计算机工程与应用,2014(4):181-185 [2] Wren C R,Azarbayejani A,Darrell T,et al.Pfinder:Real-time tracking of the human body [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780-785 [3] Barron J L,Fleet D J,Beauchemin S S.Performance of optical flow techniques [J].International journal of computer vision,1994,12(1):43-77 [4] 李刚,邱尚斌,林凌,等.基于背景差法和帧间差法的运动目标检测方法[J].仪器仪表学报,2006,27(8):961-964 [5] Stauffer C,Grimson W E L.Adaptive Background MixtureModels for Real-Time Tracking[C]∥Proc.Computer Vision and Pattern Recognition 1999(CVPR’99).June 1999 [6] Barnich O,Van Droogenbroeck M.iBe:A powerful random technique to estimate the background in video sequences[C]∥Proc.Int.Conf.Acoust.Speech Signal Process.Apr.2009:945-948 [7] 陈亮 陈晓竹,范振涛.基于 Vibe 的鬼影抑制算法[J].中国计量学院学报,2013,24(4):425-429 [8] Van Droogenbroeck M,Paquot O.Background subtraction:Experiments and improvements for ViBe [C]∥2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).IEEE,2012:32-37 [9] Barnich O,Van Droogenbroeck M.ViBe:A universal back-ground subtraction algorithm for video sequences [J].IEEE Transactions on Image Processing,2011,20(6):1709-1724 [10] Otsu N.A threshold select ion method from gray-level histo-grams [J].IEEE Transactions on System Man and Cybernetic,1979,9(1):62-66 [11] 闵华清,吕居美,罗荣华,等.基于 GMM 和 MRF 的自适应阴影检测[J].华南理工大学学报:自然科学版,2011,39(7):115-120 [12] 张德才,周春光,周强,等.基于轮廓的孔洞填充算法[J].吉林大学学报:理学版,2011,49(1):82-86 |
No related articles found! |
|