红外图像序列运动小目标的图像流检测法

Detection of Small Moving Target in Infrared Image Sequences with Image Flow Method

提出一种利用图像流分析法对红外序列图像中的运动小目标进行检测的算法．首先利用两步分离法对图像进行预处理，筛选出少量的侯选运动目标，然后利用图像流模型建立目标的运动约束方程，在多帧连续图像中检测出真正的目标运动轨迹．实验结果表明，该算法能够对小目标甚至是点目标的运动进行可靠检测．

An algorithm of small moving target detection in infrared image sequences is presented based on image flow analysis method. The image is preprocessed using two step separation method to pick out a small quantity of possible moving targets. The motion constraint equation of the targets is set up according to the image flow model. By use of the model, the true target motion trajectory is detected in multi frame successive image. The experiment results indicate that the algorithm can reliably detect small target motion, even point target one.