首页> 中文期刊> 《计算机应用研究》 >运动目标联合跟踪与分类研究综述

运动目标联合跟踪与分类研究综述

         

摘要

Target tracking and classification are the basic functions of modem tracking systems.The differing nature of the data brought the neglected connections of these two vital tasks in traditional studies and generally led to being performed separately.The joint tracking and classification made it possible that the two processes can exploit the coupling between them and enhance their respective performance.On the basis of principle analysis of the joint tracking and classification ( JTC ), categorized the algorithms into there classes according to their mechanism: the algorithm based on Bayes rule, D-S theory and Bayes risk, which were summarized separately and compared with each other.In the end, the survey pointed out the drawbacks of the existing JTC algorithms and prospects the future researches.%目标跟踪与分类是现代跟踪系统的基本功能,不同的数据特性使得传统研究经常忽视两者之间的联系而将其分开处理.联合跟踪与分类研究则充分利用两者之间的耦合关系,使之互为补充,达到提高各自精度的目的.在分析联合跟踪与分类算法基本原理的基础上,按机理将其分为基于贝叶斯推理、D-S理论和贝叶斯风险框架下的联合跟踪与分类算法,并对三种框架下的算法进行了综述与性能比较.指出了联合跟踪与分类算法研究存在的问题及进一步研究的方向.

著录项

相似文献

  • 中文文献
  • 外文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号