Mean-shift tracking algorithm and its application in optoelectronic tracking system
-
摘要:针对光电跟踪系统中实时提取运动目标脱靶量的应用需求,设计了一种基于灰度直方图的Mean-shift 图像跟踪算法,对算法中目标模型与候选模型的建立进行了改进,抑制了背景像素对目标跟踪产生的影响。算法在系统上位机Visual C+ + 6.0平台上实现,当光电跟踪系统捕获到运动目标后,利用Mean-shift图像跟踪算法跟踪运动目标,并实时将运动目标脱靶量作为伺服控制系统的输入信号,驱动跟踪器跟踪目标。实验结果表明:设计的算法可以实时、准确、有效地跟踪运动目标,使稳定后的脱靶量换算得到的角偏差量控制在30之内。Abstract:In order to fulfill the requirement to extract miss distance of moving target in real time in optoelectronic tracking system, a Mean-shift image tracking algorithm based on gray histogram is designed. The target model and the candidate model of the algorithm are improved, and the impact of background pixels on target tracking is suppressed. The algorithm is implemented in the Visual C++ 6.0 platform in the upper computer of the system. When the optoelectronic tracking system captures the moving target, the system uses the Mean-shift image tracking algorithm to track the moving target. The miss distance is used as the input signal of the servo control system to drive the tracking device to track the target. Experiment results show that the proposed Mean-shift algorithm is able to track the moving target in real time precisely and effectively so that the angle deviation can be limited within 30 arc sec.
-
[1] 侯志强, 韩崇昭. 视觉跟踪技术综述[J]. 自动化学报, 2006, 32(4):603-617. HOU ZH Q, HANG CH ZH. A survey of visual tracking[J].Acta Automatica Sin., 2006, 32(4):603-617.(in Chinese) [2] 张秉华, 张守辉.光电成像跟踪系统[M]. 成都:电子科技大学出版社, 2003. ZHANG B H, ZHANG SH H.Optical Imaging Tracking System[M]. Chengdu:University of Electronic Science and Technology of China Press, 2003.(in Chinese) [3] 吕娜, 冯祖仁. 质心迭代图像跟踪算法[J]. 西安交通大学学报, 2007, 41(12):1387-1391. LÜ N, FENG Z R. Centroid iteration image tracking algorithm[J].J. Xi'an Jiaotong University, 2007, 41(12):1387-1391.(in Chinese) [4] 孙承志, 熊天忠, 吉顺平, 等. 基于差分的光流法在目标检测跟踪中的应用[J]. 机床与液压, 2010, 38(14):59-62. SUN CH ZH, XIONG T ZH, JI SH P,et al.. Application of optical flow algorithms based on difference in target detection and tracking[J].Machine Tool Hydraulics, 2010, 38(14):59-62.(in Chinese) [5] CHEN Y Z. Mean shift, mode seeking, and clustering[J].IEEE Transactions on Pattern Analysis Machine Intelligence, 1995, 17(8):790-799. [6] 冯伟兴, 唐墨, 贺波, 等.Visual C+ +数字图像模式识别技术详解[M]. 北京:机械工业出版社, 2010. FENG W X, TANG M, HE B,et al.. Digital Image Pattern Recognition Programming Using Visual C+ +[M]. Beijing:China Machine Press, 2010.(in Chinese) [7] 毛建国, 柏方超, 沈峘, 等. 复杂场景下动态目标视觉跟踪方法[J]. 传感器与微系统, 2010, 29(3):23-28. MAO J G, BAI F CH, SHEN H,et al.. Vision based dynamic target tracking under complicated scenes[J].Transducer and Microsystem Technologies, 2010, 29(3):23-28.(in Chinese) [8] 颜佳, 吴敏渊, 陈淑珍, 等. 应用Mean Shift和分块的抗遮挡跟踪[J]. 光学 精密工程, 2010, 25(6):890-895. YAN J, WU M Y, CHEN SH ZH,et al.. Anti-occlusion tracking algorithm based on Mean Shift and fragments[J].Opt. Precision Eng., 2010, 25(6):890-895.(in Chinese) [9] 胡明昊, 任明武, 杨靖宇. 一种基于直方图模式的运动目标实时跟踪算法[J]. 计算机工程与应用, 2004(3):71-74. HU M H, REN M W, YANG J Y. A real-time moving object tracking algorithm based on histogram model[J].Computer Eng. Appl., 2004(3):71-74.(in Chinese) [10] 黄永梅, 马佳光, 付承毓. 目标速度预测在光电跟踪控制系统中的应用[J]. 红外与 工程, 2004, 33(5):477-481. HUANG Y M, MA J G, FU CH Y. Application of forecast of moving target velocity in electro-optical tracking control system[J].Infrared and Laser Eng., 2004, 33(5):477-481.(in Chinese) [11] 薛陈, 朱明, 刘春香. 遮挡情况下目标跟踪算法综述[J]. 中国光学, 2009, 2(5):388-394. XUE CH, ZHU M, LIU CH X. Review of tracking algorithms under occlusions[J].Chinese Optics, 2009, 2(5):388-394.(in Chinese) [12] 张玲, 蒋大永, 何伟, 等. 基于Mean-shift的改进目标跟踪算法[J]. 计算机应用, 2008, 28(12):3120-3122. ZHANG L, JIANG D Y, HE W,et al.. Improved target tracking algorithm based on Mean-shift[J].Computer Appl., 2008, 28(12):3120-3122.(in Chinese) [13] 彭宁嵩, 杨杰. 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. PENG N S, YANG J. Automatic selection of kernel-bandwidth for Mean-Shift object tracking[J].J. Software, 2005, 16(9):1542-1550.(in Chinese) [14] 彭宁嵩, 杨杰. Mean-Shift跟踪算法中目标模型的自适应更新[J]. 数据采集与处理, 2005, 20(2):125-129. PENG N S, YANG J. Mean-shift tracking with adaptive model update mechanism[J].J. Data Acquisition Processing, 2005, 20(2):125-129.(in Chinese) [15] 颜佳, 吴敏渊, 陈淑珍, 等. 跟踪窗口自适应的Mean Shift跟踪[J]. 光学 精密工程, 2009, 17(10):2606-2611. YAN J, WU M Y, CHEN SH ZH,et al.. Mean Shift tracking with adaptive tracking window[J].Opt. Precision Eng., 2009, 17(10):2606-2611.(in Chinese) [16] COMANICIU D, RAMESH V, MEER P. Real-time tracking of non-rigid objects using mean shift[J].IEEE, 2000, 2:142-149. [17] 王田, 刘伟宁, 韩广良, 等. 基于改进Mean-Shift的目标跟踪算法[J]. 液晶与显示, 2012, 27(3):396-400. WANG T, LIU W N, HANG G L,et al.. Target tracking algorithm based on improved Mean-Shift[J].Chinese J. Liquid Crystals and Displays, 2012, 27(3):396-400.(in Chinese) [18] 杜超, 刘伟宁, 刘恋. 一种基于卡尔曼滤波及粒子滤波的目标跟踪算法[J]. 液晶与显示, 2011, 26(3):384-389. DU CH, LIU W N, LIU L. Target tracking algorithm based on kalman filter and particle filter[J].Chinese J. Liquid Crystals and Displays, 2011, 26(3):384-389.(in Chinese) [19] 刘扬, 张云峰, 董月芳. 复杂背景下抗遮挡的运动目标跟踪算法[J]. 液晶与显示, 2010, 25(6):890-895. LIU Y, ZHANG Y F, DONG Y F. Anti-occlusion algorithm of tracking moving object in clutter background[J].Chinese J. Liquid Crystals and Displays, 2010, 25(6):890-895.(in Chinese)
点击查看大图
计量
- 文章访问数:1170
- HTML全文浏览量:195
- PDF下载量:586
- 被引次数:0