基于显著图融合的高分四号卫星光学遥感图像多运动舰船检测方法

Multiple moving ships detection method based on saliency map fusion for GF-4 satellite remote sensing image

高分四号(GF-4)卫星是目前世界上分辨率最高的静止轨道光学遥感卫星,它具有高时间分辨率、高空间分辨率和大成像幅宽等优点,可对指定区域进行连续观测。提出一种适用于GF-4卫星光学遥感图像的多运动舰船检测方法。首先,对遥感图像进行中值滤波去噪和非线性灰度拉伸;然后,通过谱残差法提取显著图;最后,使用基于加权Dempster-Shafer证据理论的图像融合方法对显著图进行融合处理后,进行舰船检测。GF-4卫星遥感图像真实数据的实验表明,本文所提方法能够对GF-4卫星光学遥感图像进行快速、准确的多运动舰船检测。

The GF-4 satellite is a geostationary-orbit optical remote sensing satellite with the highest resolution in the world.The satellite can incessantly observe the designated area with high temporal resolution,high spatial resolution,and large imaging width.In this paper,a multiple moving ships detection method for GF-4 satellite is proposed.Firstly,the median filtering denoising and non-linear gray-scale stretching are applied to the remote sensing image.Secondly,the saliency map is extracted by the spectral residual(SR)method.Finally,a fusion processing is further performed by adopting the image fusion method based on weighted Dempster-Shafer evidence theory(WDS)to detect ships.Evaluated by the experiment based on real data of GF-4 satellite,it is shown that the proposed method can detect the multiple moving ships accurately and efficiently by the GF-4 satellite image.