中文摘要：

提出了一种基于时-空域集成判决的序列图像中微小运动目标检测方法。首先,将背景杂波抑制后的残差图像沿时间轴进行累加,形成组合帧,在组合帧中经过二元假设门限判决,检测出疑似目标;然后,只对疑似目标按可能的运动方向进行空域能量集成;最后,对目标轨迹进行统计判别。算法的性能分析和实验仿真结果表明,该方法在保证较高检测概率的同时,大大减少了运算量,有利于实时实现。

英文摘要：

Based on tempo-spatial integrating and statistical decision,a fast detection algorithm is proposed for small moving targets.In the algorithm,the background clutter is firstly suppressed,and by accumulating a certain number of the obtained residual images,a composite frame is constructed.Then using the binary threshold decision,the suspected targets are detected.Finally,in spatial domain,the small moving target is detected by integrating signal energy along the possible moving target trajectory.The theoretic...