JIN Yong, WANG Zhen, WANG Zhao-ba, CHEN You-xing
（Science and Technology on Electronic Test & Measurement Laboratory, North University of China, Taiyuan 030051, China）
Abstract： In practical application, mean shift tracking algorithm is easy to generate tracking drift when the target and the background have similar color distribution. Based on the mean shift algorithm, a kind of background weaken weight is proposed in the paper firstly. Combining with the object center weight based on the kernel function, the problem of interference of the similar color background can be solved. And then, a model updating strategy is presented to improve the tracking robustness on the influence of occlusion, illumination, deformation and so on. With the test on the sequence of Tiger, the proposed approach provides better performance than the original mean shift tracking algorithm.
Key words： object tracking; mean shift; color histogram; model updating
CLD number： TP391.41Document code： A
Article ID： 1674-8042（2016）02-0171-05 doi： 10.3969/j.issn.1674-8042.2016.02.013
References
［1］Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(2): 564-577.
［2］Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift. In: IEEE Conference Computer Vision and Pattern Recognition, 2000, 2: 142-149.
［3］SONG Yi, LI Shu-xiao, ZHU Cheng-fei, et al. Erratum: Invariant foreground occupation ratio for scale adaptive mean shift tracking. IET Computer Vision, 2016, 10(2): 172.
［4］ZHANG Xie-hua, ZHANG Shen, TIAN Min. Research on the “Selective Color Histogram” for moving object tracking. Journal of Chinese Computer Systems, 2009, 30(9): 1864-1868.
［5］PENG Ning-song, YANG Jie, LIU Zhi, et al. Automatic selection of kernel-bandwidth for mean shift object tracking. Journal of Software, 2005, 16(9): 1542-1550.
［6］LI Pei-hua. An improved mean shift algorithm for object tracking. Acta Automatica Sinica, 2007, 33(4): 347-354.
［7］YU Wang-sheng, TIAN Xiao-hua, HOU Zhi-qiang, et al. Multi-scale mean shift tracking. IET Computer Vision, 2015, 9(1): 110-123.
［8］Birchfield S T， Rangarajan S. Spatiograms versus histograms for region-based tracking. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, 2005, 2: 1158-1163.
［9］ZHOU Hui-yu, YUAN Yuan, SHI Chun-mei. Object tracking using SIFT features and mean shift, Computer Vision and Image Understanding, 2009, 25(5): 345-352.
一种改进的基于双权值颜色直方图的均值漂移跟踪算法
金永， 王振， 王召巴， 陈友兴
（中北大学 电子测试技术重点实验室， 山西 太原 030051）
摘要:在实际应用中， 当目标与背景的颜色相似时， 均值漂移跟踪算法容易产生跟踪漂移现象。 本文基于均值漂移算法， 首先提出一种背景削弱权值， 结合基于核函数的目标中心加权， 有效解决由相似背景带来的跟踪干扰。 然后提出一种模板更新策略， 提高目标在遮挡、 光照、 形变等干扰下的跟踪鲁棒性。 由老虎图像序列实验可知， 提出的改进算法具有更好的跟踪效果。
关键词:目标跟踪； 均值漂移； 颜色直方图； 模板更新
引用格式：JIN Yong, WANG Zhen, WANG Zhao-ba, et al. An improved mean shift tracking algorithm based on double weighted color histogram. Journal of Measurement Science and Instrumentation, 2016, 7(2)： 171-175. ［doi： 10.3969／j.issn.1674-8042.2016.02.013］
[full text view]
