期刊文献+

基于水平集的TLD目标跟踪改进算法 被引量:2

An improved TLD target tracking algorithm based on level set
在线阅读 下载PDF
导出
摘要 TLD算法是一种新颖的长期目标跟踪算法,针对算法中检测器采用特征没有充分考虑跟踪过程中目标的表观、区域轮廓的变化及基于窗口扫描影响效率等问题,在TLD算法的基础上,加入演化机理,基于水平集对其进行改进。结合边缘和区域信息的多尺度水平集方法,引入目标轮廓信息,在有效克服灰度不均匀图像的同时,提高了目标跟踪的适应性及精度;根据轮廓检测结果,引入目标运动方向检测算子,对目标运动方向及其在当前帧中的位置进行估计,减少扫描窗口的同时提高目标辨识能力。通过实验对原始TLD算法及改进的算法进行了比较。实验结果表明,改进后的方法跟踪速度有提升,对目标跟踪的适应性更强,跟踪精度更高。 The tracking-learning-detection (TLD) algorithm is a novel long-term target tracking al- gorithm, however, the detectors do not fully consider contour changes in the target tracking process, and window-based scanning affects the efficiency. We introduce the evolution mechanism to improve the TLD algorithm based on level set. The multi-scale level set method combines the edge information with the region information, which improves the adaptation and precision of target tracking while effectively overcomes gray uneven images. According to the test results of the outline, we introduce the motion de- tection operator of the target direction to estimate the movement direction of the target and its position in the current frame, which can reduce the scan window while improving the ability of target identification. Experimental results show that the improved method can enhance the tracking speed, and has stronger adaptability and higher tracking accuracy.
出处 《计算机工程与科学》 CSCD 北大核心 2017年第5期984-991,共8页 Computer Engineering & Science
基金 中央高校基本科研业务费专项资金(DC201502060303 DC201501075)
关键词 目标跟踪 TLD 多尺度水平集 适应性 运动检测 target tracking tracking-learning-detection (TLD) multi-scale level set adaptability motion detection
作者简介 张丹(1987-),女,辽宁葫芦岛人,硕士,助理工程师,研究方向为图像处理和计算机视觉。E-mail:Zhangdan.4@163.com 陈兴文(1969-),男,辽宁大连人,硕士,教授,研究方向为计算机视觉。E-mail:zhangdan@dlnu.edu.cn
  • 相关文献

参考文献2

二级参考文献27

  • 1冈萨雷斯.数字图像处理[M].北京:电子工业出版社,2005.
  • 2ATLAS S W. Magnetic resonance imaging of the brain and spine[ M]. 3rd ed. Philadelphia Lippincott Williams and Wilkins,2002.
  • 3OSHER S, SETHIAN J A. Fronts propagating with cura- ture-dependent speed: algorithms based on Hamilton-Ja- cobi formulations [ J ]. Journal of Computational Physics, 1988,79 : 12-49.
  • 4CHAN T, VESE L. Active contours without edges [J]. IEEE Transaction on Image Processing, 2001,10 ( 2 ) : 266 -277.
  • 5CHENG L, YANG J, FAN X. A generalized level set for- mulation of the Mumford-Shah functional for brain MR im- age segmentation [ M ]. Heidelberg, Berlin : Springer,2005.
  • 6LI CH M, XU CH Y , GUI CH F, et al. Level set evolution without re-initialization: A new variational formulation [ J]. Computer Society Conference On Computer Vision and Pattern Recognition,2005.
  • 7ZHANG K H , SONG H H , ZHANG L . Active contours driven by local image fitting energy [ J ]. Pattern Recogni- tion, 2009,43 : 1199-1206.
  • 8KHALIFA F, EL-BAZ A, GIMEL G, et al. Non-invasive image-based approach for early detection of acute renal rejection [ J ]. Medical Image Computing and Computer Assisted Intervention,2010, Part I, LNCS 6361 : 10-18.
  • 9LI CH M, KAO C Y, GORE J C, et al. Minimization of Region-Scalable fitting energy for image segmentation [ J ]. IEEE Transactions on Image Processing, 2008,17 (10) :1940-1949.
  • 10LI CH M, HUANG R, DING ZH H, et al. A variational level set approach to segmentation and bias correction ofimages with intensity inhomogeneity [ J ]. Medical Image Computing and Computer Assisted Intervention, 2008, Part II, LNCS 5242 : 1083-1091.

共引文献4

同被引文献6

引证文献2

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部