期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于TLD的动态背景下视觉跟踪技术研究 被引量：1

Study of Visual Tracking Technology in Dynamic Background Based on TLD
下载PDF
导出
摘要 随着科学技术的不断发展,具有摄像功能的移动设备越来越多,这给动态场景下的视觉跟踪技术开辟了广阔的应用前景。TLD(Tracking-Learning-Detection)算法是一种新颖、高效的长时间视觉跟踪算法。在该算法的基础上对动态场景下的视觉跟踪技术进行研究。首先对TLD算法的主要特点、框架流程进行了总结;然后重点分析了TLD算法综合模块的机制,针对原算法在跟踪过程中出现漂移甚至跟踪失败的问题,对算法综合模块的整合机制提出改进;最后经实验论证,改进算法取得了预期的效果,在不影响运行速度的情况下提高了跟踪的稳定性和识别率。 With the continuous development of science and technology, more and more mobile devices are equipped with camera, which creates a broad application prospect for the dynamic background visual tracking technology＇. The TLD （Tracking-Learning- Detection） algorithm is a novel, efficient and long-term visual tracking algorithm. In this paper, the visual tracking technology is studied based on this algorithm. First of all, the main characteristics and framework of TLD are summarized. Secondly, the mecha- nism of TLD＇s integrator is analyzed. Moreover, aiming at the original algorithm＇s problems, such as drifting and failure, the im- provement on integration mechanism of integrator is proposed. Finally, the experiment demonstrates that the developed algorithm ob- tains expected effects, and it improves the stability and recognition rate witbout affecting the operation speed.
作者 成正国 潘广贞
机构地区 中北大学计算机与控制工程学院
出处 《电视技术》 北大核心 2015年第7期111-114,共4页 Video Engineering
关键词 视觉跟踪算法 动态背景 TLD 综合模块 visual tracking algorithm dynamic background TLD integrator
分类号 TP391.4 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献14

  • 1DELL N, FRANCIS I, SHEPPARD H, et aL Field evaluation of a camera-based mobile health system in low-resource settings[ C ]// Proc. 16th International Conference on Human-computer Interaction with Mobile Devices & Services. New York : ACM Press, 2014 : 33- 42.
  • 2鹿文浩,王生进.鲁棒的车载摄像头对向车辆检测与跟踪方法[J].清华大学学报（自然科学版）,2013,53(11):1509-1514. 被引量：3
  • 3KURNIAWAN M N, WIDIYANTO D. Implementation of image pro- cessing algorithms and GLVQ to track an object using AR Drone camera [ J]. Journal of Computer Science and Information, 2014, 7 (2) : 111-118.
  • 4CHANG Faliang, ZHANG Guoqiang, WANG Xiaolin, et al. PTZ camera target tracking in large complex scenes[ C ]//Proe. 2010 8th World Congress on Intelligent Control and Automation. Jinan: IEEE Press, 2010: 2914-2918.
  • 5SHAN C F, PORIKLI F, XIANG T, et al. Video analytics for busi- ness intelligence [ M ]. Berlin Heidelberg: Springer, 2012.
  • 6YANG Hanxuan, SHAO Ling, ZHENG Feng, et al. Recent ad- vances and trends in visual tracking: a review [ J]. Neurocomputing, 2011,74(18) : 3823-3831.
  • 7YILMAZ A, JAVED O, SHAH M. Object tracking: a survey [J]. ACM Computing Surveys, 2006, 38 (4) : 1-45.
  • 8白晓方,杨卫,陈佩珩.一种改进的运动目标检测与跟踪方法[J].电视技术,2014,38(1):180-182. 被引量：12
  • 9孙斌,黄神治.移动背景下运动目标检测与跟踪技术研究[J].电子测量与仪器学报,2011,25(3):206-210. 被引量：45
  • 10KALAL Z, MATAS J, MIKOLAJCZYK K. Online learning of ro- bust object detectors during unstable tracking [ C]//Proc. IEEE On-line Learning for Computer Vision Workshop. New York : IEEE Press, 2009:1417-1424.

二级参考文献33

  • 1SHEN S A, TONG M L, DENG H L, et al. Model based human motion tracking using probability evolutionary algorithm [J]. Pattern Recognition Letters, 2008, 29(13): 1877-1886.
  • 2SEO D W, CHAE H U, KIM B W, et al. Human tracking based on multiple view homography [J]. Journal of Universal Computer Science, 2009, 15(13): 2463-2484.
  • 3SORWAR G, MURSHED M, DOOLEY L. Fast global motion estimation using iterative least-square technique[C]. The 4th IEEE Pacific-Rim Conference On Multimedia Singapore, 2003, 1: 282-286.
  • 4HE Y W, FENG B, YANG S. Fast global motion estimation for global motion compensation coding [C]. Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS), 2001, 2: 233-236.
  • 5CHEUNG H K, SIU W C. Fast global motion estimation for sprite generation [C]. the IEEE International Symposium on Circuits and Systems, 2002, 3: 26-29.
  • 6RICHARD A, STEVEN M K, PETRE S. Estimation of the parameters of a bilinear model with applications to submarine detection and system identification [J]. Digital Signal Processing, 2007, 17(4): 756-773.
  • 7SMITH S M, BRADY J M. SUSAN-a new approach to low level image processing [J]. Computer Vision, 1997, 23(1): 45-78.
  • 8DAVID G L. Distinctive image features from scale-invariant key-points [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
  • 9MORAVEC H E Visual mapping by a robot rover [C]. International Joint Conference on artificial Intelligence, 1979: 598-600.
  • 10HARRIS C, STEPHENS M. A combined corner and edge detector [C]. Fourth AlveyVision Conference, 1988: 17-151.

共引文献57

同被引文献25

  • 1KALAL Z, MIKOLAJCZYK K, MATAS J. Forward-back- ward error: automatic detection of tracking failures [ C l// Proc. 20th International Conference on Pattern Recognition (ICPR). [S. 1.] :IEEE,2010:2756-2759.
  • 2KALAL Z, MATAS J, MIKOLAJCZYK K. Online learning of robust object detectors during unstable tracking[ C]// Proe. IEEE 12th International Conference on Computer Vi- sion Workshops ( ICCV Workshops) . [ S. 1. ] : IEEE, 2009 : 1417-1424.
  • 3KALAL Z, MATAS J, MIKOLAJCZYK K. Pn learning: bootstrapping binary classifiers by structural constraints [C]// Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . [ S. 1. ] : 1EEE,2010:49-56.
  • 4KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learn- ing-detection[ J]. IEEE transactions on pattern analysis and machine intelligence,2012,34(7) : 1409-1422.
  • 5NEMADE B, BHARADI V A. Adaptive automatic track- ing, learning and detection of any real time object in the vid- eo stream[ C ]// Proc. IEEE 5th International Conference on Confluence The Next Generation Information Technology Summit (Confluence). [ S. 1.] :IEEE,2014: 569-575.
  • 6HAILONG W, GUANGYU W,JIANXUN L. An improved tracking- learning - detection method [ C ]// Proc. IEEE 34th Chinese Control Conference (CCC). [ S. 1. ] : IEEE, 2015 : 3858-3863.
  • 7ZHANG P,SUN Y Q,YA-LI W U,et al. A parallel imple-mentationofTLDalgorithmusingCUDA[C]//2013全国高性能计算学术年会.桂林:[出版者不详],2013:220-224.
  • 8SUN C,ZHU S,LIU J. Fusing Kalman filter with TLD algo- rithm for target tracking [ C //Proc. 2015 34th Chinese Control Conference (CCC). [ S. 1. ] :IEEE,2015:3736- 3741.
  • 9NEBEHAY G. Robust object tracking based on tracking- learning-detection [ EB/OL]. [ 2015 - 12-18 ]. http:// www. gnebehay, corn/publications/master_ thesis/master thesis, pdf.
  • 10CHENG S,LIU G,SUN J. Robust and fast tracking-learn- ing-detection [ C 1//Proc. 2015 International Conference on Computer Science and Intelligent Communication. [ S. 1. ] : Atlantis, 2015.

引证文献1

电视技术
2015年 第7期

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