计算机科学 ›› 2014, Vol. 41 ›› Issue (12): 280-282.doi: 10.11896/j.issn.1002-137X.2014.12.060
成新田,唐振民
CHENG Xin-tian and TANG Zhen-min
摘要： Mean-Shift算法是一种简单高效的目标识别算法,但是不能有效地识别被遮挡的目标和有尺度变化的目标。基于仿射变换,提出了一种尺度自适应的机器人目标跟踪算法。定义了转角点,并根据转角点匹配对目标进行区分,最后通过仿射变换识别出目标的尺度变化。与其它相关算法相比,该算法能有效地识别被跟踪目标的遮挡问题；当被跟踪目标的尺度发生改变时,该算法仍然能准确地对目标进行识别。分析表明,当视屏流中每秒的图像小于25帧并且目标的图像小于2×104个像素时,该算法可以用于目标的实时跟踪。
| [1] Li X R,Jilkov V P.Survey of maneuvering target tracking.Part I.Dynamic models[J].IEEE Transactions on Aerospace and Electronic Systems,2013,39(4):1333-1364 [2] 邵文坤,黄爱民,韦庆.目标跟踪方法综述[J].影像技术,2006 (1):17-20 [3] Comaniciu D,Ramesh V,Meer P.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):564-577 [4] Ning J,Zhang L,Zhang D,et al.Robust mean-shit tracking with corrected background-weighted histogram[J].IET Computer Vision,2012,6(1):62-69 [5] Mohammadi S A,Amoozegar S,Jolfaei A,et al.Enhanced adaptive bandwidth tracking using mean shit algorithm[C]∥Proceedings of the IEEE 3rd International Conference on Communication Software and Networks (ICCSN’11).May 2011:494-498 [6] Bhattacharyya A.On a measure of divergence between two multinomial populations[J].Sankhyā:The Indian Journal of Statistics,1946,7(4):401-406 [7] Peng N,Yang J,Liu Z,et al.Mean-Shift跟踪算法中核函数窗宽的自动选取[J].软件学报,2005,16(9):1542-1550 [8] Bradski G R.Computer vision face tracking for use in a perceptual user interface[C]∥Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV’98).1998:214-219 [9] Hu J,Juan C,Wang J.A spatial-color mean-shit object tracking algorithm with scale and orientation estimation[J].Pattern Re-cognition Letters,2008,29(16):2165-2173 [10] Zhao C,Knight A,Reid I.Target tracking using mean-shift and affine structure[C]∥19th International Conference on Pattern Recognition(ICPR 2008).IEEE,2008:1-5 [11] Leichter I,Lindenbaum M,Rivlin E.Tracking by affine kerneltransformations using color and boundary cues[J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2009,31(1):164-171 |
| No related articles found! |
|
||
首页