光子学报, 2014, 43 (5): 0510003, 网络出版: 2014-06-03   

带宽自适应的均值漂移红外目标跟踪算法

Bandwidth-adaptive Mean Shift Infrared Target Tracking Algorithm
作者单位
中国电子科技集团第二十八研究所,南京 210007
摘要
当目标尺度发生变化时,传统均值漂移跟踪因窗口尺寸不变导致跟踪目标丢失.为解决该问题,提出一种带宽自适应的均值漂移跟踪算法.该算法在均值漂移框架下提取目标的形状特征,根据目标形状变化自适应的修正核函数带宽,并更新目标模板.实验结果表明,改进算法能很好地适应尺寸变化的目标,能有效提高红外目标的跟踪准确度.
Abstract
For the fixed-bandwidth windows, the tracking target will be lost in traditional mean shift algorithm with target scale changed. To solve this problem, an adaptive-bandwidth mean shift tracking algorithm was proposed. The shape features were extracted under the algorithm in the framework of mean shift, the bandwidth was adjusted adaptively based on target shape motions, and the target template was updated. Experimental results indicate that the proposed algorithm can track the target with scale changed and improve the target tracking precision effectively.
参考文献

[1] 程建,周越.基于粒子滤波的红外目标跟踪[J].红外与毫米波学报, 2006,25(2):113-117.

    CHENG Jian, ZHOU Yue. Infrared object tacking based on particle filters[J]. Journal of Infrared and Millimeter Waves, 2006, 25(2): 113-117.

[2] 凌建国,刘尔琦,杨杰,等.基于滤波器的红外小目标运动预测和跟踪方法[J].红外与毫米波学报, 2005,24(5):366-369.

    LING Jian-guo, LIU Er-qi, YANG Jie, et al. Approach of infrared small target motion prediction and tracking based on filter[J]. Journal of Infrared and Millimeter Waves, 2005, 24(5): 366-369.

[3] SHI Hai-hua, XIANG Wei. Object tracking using improved meanshift algorithm combined with kalman filter on independent visual robotic fish[J]. Applied Mechanics and Materials, 2013, 333: 1030-1033.

[4] Paul Rui. A new fuzzy based algorithm for solving stereo vagueness in detecting and tracking people[J]. International Journal of Approximate Reasoning, 2012, 53(4): 693-708.

[5] LI Yun-dong, ZHAO wei-gang. Adaptive updating of kernel band-width for mean-shift tracking[J]. Journal of Computational Information Systems, 2012, 22(8): 9569-9579.

[6] 余春艳, 吴立峤, 李建明. 基于像素序列型态的适应性背景重构算法[J]. 光子学报, 2011, 40(7): 1036-1045.

    YU Chun-yan, WU li-qiao, LI Jian-ming. A background reconstruction algorithm based on pixel sequence pattern classification[J]. Acta Photonica Sinica, 2011, 40(7): 1036-1045.

[7] 赵高鹏, 薄煜明.基于特征自适应选择的金字塔均值漂移跟踪方法[J]. 光子学报,2011, 40(1):154-160.

    ZHAO Gao-peng, BO Yu-ming. Pyramid mean shift tracking algorithm based on adaptive feature selection[J]. Acta Photonica Sinica, 2011, 40(1): 154-160.

[8] 王明佳, 武治国, 韩广良, 等. 自适应窗口选取的Mean shift目标跟踪[J]. 光子学报,2012,41(1):67-71.

    WANG Ming-jia, WU Zhi-guo, HAN Guang-liang, et al. Mean shift object tracking of adaptive tracking window[J]. Acta Photonica Sinica, 2012, 41(1): 67-71.

[9] 李熙莹,倪国强. 红外图像的光流计算[J].光电工程, 2002,31(2): 189-193.

    LI Xi-ying, NI Guo-qiang. A new tracking method for IR targets[J]. Opto-Electronic Engineering, 2002, 31(2): 189-193.

[10] COMANICIU D, RAMESH V, MEER P. Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577.

[11] POLAT E. Anonparametric adptive tracking algorithm based on multiple feature distributions[J]. IEEE Transactions on Multimedia, 2006, 8(6): 1156-1163.

[12] WANG J Q, YAGI Y. Integrating shape and color features for adaptive real-time object tracking[C]. Proceedings of IEEE Conference on Robotics and Biomimetics. Kunming: IEEE Ras, 2006: 1-6.

[13] 魏坤, 赵永强, 潘泉, 等.基于均值漂移和粒子滤波的红外目标跟踪[J]. 光电子激光,2008,19(2):213-217.

    WEI Kun, ZHAO Yong-qiang, PAN Quan, et al. IR target tracking based on mean shift and partide filter[J]. Journal of Optilectronics Laser, 2008, 19(2): 213-217.

王寿峰, 白俊奇. 带宽自适应的均值漂移红外目标跟踪算法[J]. 光子学报, 2014, 43(5): 0510003. WANG Shou-feng, BAI Jun-qi. Bandwidth-adaptive Mean Shift Infrared Target Tracking Algorithm[J]. ACTA PHOTONICA SINICA, 2014, 43(5): 0510003.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!