复杂背景下的红外小目标检测  

Detecting dim moving infrared target in the clutter background

作　　者：陈振华[1] 周锐锐[1] 毕笃彦[1] 

机构地区：[1]空军工程大学工程学院四系信号与信息处理实验室,陕西西安710038

出　　处：《中国体视学与图像分析》2006年第3期230-233,共4页Chinese Journal of Stereology and Image Analysis

摘　　要：针对复杂背景红外序列中小目标检测问题,提出了基于形态学Top-hat算子和运动连续性的目标检测算法。形态学中的Top-hat算子是一种极好的高通滤波算子,开Top-hat算子能检测图像中的峰,而闭Top-hat算子则能检测图像中的谷。通过对Top-hat算子选择合适的结构元,就可以将候选的目标从复杂的背景中提取出来,然后利用序列图像中运动目标的连续性和轨迹的一致性筛选出真正的目标。试验结果表明,该方法能有效抑制背景噪声、检测并跟踪红外小目标。A new method based on morphology top-hat operator and moving continuity of moving target is presented for solving detecting of moving small target with clutter background in infrared image sequence. The morphological Top-Hat operation is a high-pass filtering operation with good performances. First suppresses the background clutter and segmenting the possible targets by Top-hat operator, then filtrating the true targets according to the principle of moving continuity and trajectory consistency of moving targets in the sequences. The experiment results show that the method can effectively and reliably detect the moving point target with low SNR.

关 键 词：红外图像序列 小目标检测 TOP-HAT算子 

分 类 号：TN215[电子电信—物理电子学]