Abstract
The generic Meanshift is susceptible to interference of background pixels with the target pixels in the kernel of the reference model, which compromises the tracking performance. In this paper, we enhance the target color feature by attenuating the background color within the kernel through enlarging the pixel weightings which map to the pixels on the target. This way, the background pixel interference is largely suppressed in the color histogram in the course of constructing the target reference model. In addition, the proposed method also reduces the number of Meanshift iterations, which speeds up the algorithmic convergence. The two tests validate the proposed approach with improved tracking robustness on real-world video sequences.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kinjal A. Shah, Harsh K. Kapadia, Vipul A. Shah, and Maurya N. Shah. Application of Meanshift algorithm for license plate localization. 2011 Nirma University International Conference on Engineering (NUiCONE 2011), 1(2011)5, 8–10.
Huiyu Zhou, Yuan Yuan, and Chunmei Shi. Object tracking using SIFT features and Mean Shift, Computer Vision and Image Understanding, 113(2009)3, 345–352.
Tao Zhang and Canhui Cai. A face tracking algorithm based on multiple feature Mean Shift. Journal of Electronics & Information Technology, 31(2009)8, 1816–1820 (in Chinese). 张涛, 蔡灿辉.基于多特征Mean Shift 的人脸跟踪算法. 电子与信息学报, 31(2009)8, 1816–1820.
Xiaohe Li, Taiyi Zhang, Xiaodong Shen, and Jiancheng Sun. Mean Shift object tracking based on background-weighted spatio-grams. Journal of Optoelectronics Laser, 21(2010)5, 767–771 (in Chinese). 李小和, 张太镒, 沈晓东, 孙建成. 基于加权空间直方图的均值漂移目标跟踪.光电子·激光, 21(2010)5, 767–771.
Xinhong Wang, Jingtian Wang, Ming Yang, et al.. Mean Shift tracking algorithm based on spatial edge orientation histograms. Journal of Image and Graphics, 13(2008), 586–592 (in Chinese). 王新红, 王晶田, 敏杨等. 基于空间边缘方向直方图的 Mean Shift 跟踪算法. 中国图象图形学报, 13(2008)3, 586–592
Yufeng Zheng, Xiurong Ma, Xiaolin Zhao, et al.. Mean Shift target tracking algorithm based on color and edge features. Journal of Optoelectronics Laser, 22(2011)8, 1231–1235 (in Chinese). 郑玉凤, 马秀荣, 赵晓琳等. 基于颜色和边缘特征的均值迁移目标跟踪算法. 光电子·激光, 22(2011)8, 1231–1235.
Yongmei Cheng, Jinxing Wang, Kun Wei, et al.. Visible/Infrared dual-channel target tracking based on weighted Mean-shift. Acta Photonica Sinica, 39 (2010)2, 357–362 (in Chinese).. 程咏梅, 王进行, 魏坤等. 基于加权Mean-shift 可见光 /红外双通道目标跟踪. 光子学报, 39(2010)2, 357–362.
Junyi Zuo, Yan Liang, Quan Pan, et al.. Camshift tracker based on multiple color distribution models. Acta Automatica Sinica, 34(2010)7, 736–742 (in Chinese). 左军毅, 梁彦, 潘泉, 等. 基于多个颜色分布模型的 Camshift 跟踪算法. 自动化学报, 34(2010)7, 736–742.
Y. Cheng. Mean shift, mode seeking and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(1995)8, 790–799.
D. Comaniciu, V. Ramesh, and P. Meer. Kernel based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2003)5, 564–77.
J. Ning, Lei Zhang, David Zhang, and C. Wu. Robust mean shift tracking with corrected background weighted histogram. IET Computer Vision, 6(2012)1, 62–69.
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the Program for Technology Innovation Team of Ningbo Government (No. 2011B81002) and the Ningbo University Science Research Foundation (No. xkl11075).
Communication author: Chen Ken, born in 1962, male, Ph.D., Associate Professor.
About this article
Cite this article
Chen, K., Song, K., Kyoungho, C. et al. Optimized meanshift target reference model based on improved pixel weighting in visual tracking. J. Electron.(China) 30, 283–289 (2013). https://doi.org/10.1007/s11767-013-2168-5
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11767-013-2168-5