一种复杂海天背景下的红外舰船目标自动检测方法  

An Automatic Target Detection Method for Infrared Ship in Complex Sea-Sky Background

作　　者：王鹏[1,2] 吕高杰[3] 龚俊斌[1,2] 田金文[1,2] 

机构地区：[1]华中科技大学图像识别与人工智能研究所,武汉市珞喻路1037号430074 [2]华中科技大学多谱信息处理技术国防科技重点实验室,武汉市珞喻路1037号430074 [3]中国一航洛阳电光设备研究所火力控制技术国防科技重点实验室,洛阳市凯旋西路25号471009

出　　处：《武汉大学学报（信息科学版）》2011年第12期1438-1441,共4页Geomatics and Information Science of Wuhan University

基　　金：航空基金资助项目(20085179008)

摘　　要：提出了一种红外舰船目标检测算法。首先,利用设计好的频域组合高通滤波器对原始红外图像进行处理,以得到舰船目标可能存在的区域即目标潜在区;然后,对获得的目标潜在区进行尺度自适应的局部阈值分割,进而提取出较为完整的舰船目标或者虚假目标;最后通过检测吃水线特征来筛选出正确的舰船目标。实验结果表明,此算法能够有效地检测出复杂海天背景条件下的红外舰船目标,且具有一定的时效性。A new automatic target detection algorithm is proposed to detect infrared ship in complex sea-sky background.To procure the potential target regions,in the method,a combined high-pass filter in frequency domain is designed to filter original image.Afterwards,a scale-adaptive local threshold segmentation method is presented for extracting integral possible ship based on the potential target regions.Waterline detection is employed to distinguish correct ship finally.As the new method does not depend on the information of sea-sky line position and high brightness ship chimney or engine,its performance has been improved greatly.Experimental results indicate that the proposed method not only demonstrates reliable target detection capability for infrared ship in complex sea-sky background,but also shows efficiency.

关 键 词：红外舰船目标检测 目标潜在区提取 尺度自适应局部阈值分割 吃水线检测 

分 类 号：P237.4[天文地球—摄影测量与遥感]