摘要
该文提出了一种快速检测、跟踪序列图像中低信噪比(<2)点目标的算法。该算法有机地结合了遗传算法与多级假设检验算法。仿真结果表明应用此算法,可快速实现信噪比小于2的点目标的检测与跟踪。文中根据低信噪比点目标检测的难点,设计了合适的编码方案,提出了合格个体保留法,选择了合适的遗传算子。
A fast algorithm is proposed for tracking low observable point-source targets of unknown position and velocity in a digital image sequence. It combines genetic algorithms and multistage hypothesis tracking method. The simulation results show that it can detect and track targets computational efficiently with SNR<2. According to the difficulties of tracking point source targets with low SNR, coding and genetic operation are designed for this problem. Eligible points retaining as a new genetic operation is proposed here.
基金
国家部级基金
国家重点实验室基金
图像信息处理与智能控制教育部开放研究实验室基金资助课题
关键词
遗传算法
点目标跟踪
低信噪比
图像处理
Genetic algorithms, Multistage hypothesis, Sequential images, Detecting and tracking dim point-source target
