首页 | 本学科首页   官方微博 | 高级检索  
     

TLD目标跟踪算法研究
引用本文:高帆,吴国平.TLD目标跟踪算法研究[J].电视技术,2013,37(11).
作者姓名:高帆  吴国平
作者单位:中国地质大学(武汉)信息与通信工程,湖北武汉,430074
基金项目:基于流形学习进行图结构设计的高光谱图像分类计数研究;青年科学基金项目
摘    要:在TLD (Tracking Learning Detector)算法的基础上,提出了一种基于Online MIL(Online Multiple Instance Learning)的TLD目标跟踪算法.算法使用改进的MIL跟踪器进行目标跟踪,提高了目标在被遮挡情况下跟踪的鲁棒性.另外,在学习机制部分,目标位置的决策策略使用了跟踪结果优先的原则,使算法能适应出现类似目标时的跟踪.实验结果表明,该方法能够长时间准确地跟踪目标,并在出现类似目标时;跟踪效果较好.此外,改进后的算法在跟踪的稳定性和跟踪效率上较原算法提高了1倍.

关 键 词:TLD  Online  MIL  目标跟踪
收稿时间:2012/12/17 0:00:00
修稿时间:1/9/2013 12:00:00 AM

TLD Target Tracking Algorithm
gaofan and wuguoping.TLD Target Tracking Algorithm[J].Tv Engineering,2013,37(11).
Authors:gaofan and wuguoping
Affiliation:China University of Geosciences(Wu han),China University of Geosciences(Wu han)
Abstract:On the basis of TLD algorithm,this paper proposed an TLD method based on online mil algorithm.we use the improved MIL tracking algorithm to improve the robustness in object tracking through occlusion;And in the part of learning ,in order to tracking a similar target,we change the decision strategies of the target location,and use the principle of priority of tracking results to decide the target location.The experimental results show that the method can be long and accurate tracking targets and better tracking similar goals appear;In addition the improved algorithm in tracking stability and tracking efficiency increased one times compared with the original algorithm.
Keywords:TLD  Online MIL  target tracking
本文献已被 万方数据 等数据库收录!
点击此处可从《电视技术》浏览原始摘要信息
点击此处可从《电视技术》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号