论文部分内容阅读
本文讨论了利用传感器获取的有关目标的多特征数据来实现多目标关联跟踪的方法．通过品质函数的概念定义一种关联测度，并且阐明这一测度是常规关联决策的推广关联测度可以取0到1之间的任何实数值来表示相关程度．考虑到实际情况下某些特征数据可能不易持续获得，引入了有效因子来处理特征数据缺损的情况．本文采用了计算机仿真实验对比的方法研究了多特征数据关联跟踪的效果．
In this paper, we discuss the multi-target correlation tracking method based on the multi-characteristic data about the target obtained by the sensor. The definition of a correlation measure by the concept of quality function and clarifying that this measure is a generalization of conventional correlation decision can indicate the degree of correlation by any real number from 0 to 1. Taking into account the fact that some of the characteristic data may not be easily obtained continuously, an effective factor is introduced to deal with the characteristic data defect. In this paper, a computer simulation experiment is used to compare the effect of multi-feature data association tracking.