红外序列图像运动小目标检测算法  

Detection Algorithm for Small Moving Targets in Infrared Image Sequences

作　　者：于素芬[1] 周洪武[1] 柳毅[2] 

机构地区：[1]中国航空工业洛阳电光设备研究所,河南洛阳471009 [2]西北工业大学电子工程系,陕西西安710072

出　　处：《红外技术》2005年第3期232-234,共3页Infrared Technology

摘　　要：利用红外序列图像小目标运动的连续性进行背景恢复,滤除背景以提高信噪比,在门限检测后对图像进行边缘滤波以进一步提高检测概率,最后再一次运用目标的运动特性确认目标,减小虚警率,从而有效地检测出目标。实验结果证明,这种算法检测率高,而且计算简单,易于硬件实现。The recovery of background depends on the continuity of the movement of small targets in infraredimage sequences. After filtering the background and threshold segmentation,the SNR is enhancedconsiderably. In order to increase the probability of the detection, the questionable targets on the edge ofimages will be eliminated. At last,the true target can be accurately detected after the speciality of movingtargets was applied once again. The effectiveness of the algorithm was proved by the experimental results forseveral infrared image sequences.

关 键 词：红外序列图像 运动小目标 检测算法 目标运动 高信噪比 检测概率 门限检测 运动特性 硬件实现 连续性 虚警率 检测率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP391.41[自动化与计算机技术—计算机科学与技术]