动态规划算法在运动点目标检测中的应用研究

Dynamic Programming Algorithm for Detecting Moving Point Targets

序列图像中低信噪比运动点目标的实时检测算法,是许多实时处理系统中的关键算法之一。该文在对面临的实际问题与对检测算法分析的基础上,详细阐述和研究了利用LS线性预测器的动态规划能量累积算法,并根据仿真实验的效果,指出此算法较直接动态规划能量累积算法可最大程度地降低能量扩散,减少团聚在目标周围的虚警目标点,十分利于后续轨迹关联检测处理.

The real-time detection algorithm of moving point target in image sequences is one of key algorithms in many real-time processing systems. After the analysis of real background and the demand of the detection algorithm, this paper presents a research of the dynamic programming with LS linear predictor for detecting low SNR moving targets. With the result of simulation test, it can be pointed out that the introduced algorithm can effectively suppress the target energy pervasion and reduce the false alarms around the real target. The result is very suitable for the point-track predicting and matching algorithm for detecting the target trajectory.