基于目标特征的光学遥感图像舰船检测方法

A Method of Ships Detection from Optical Remote Sensing Images Based on Feature Detection

针对大场景、高分辨率的光学遥感图像舰船目标检测中,传统的阈值检测方法效果不佳,而恒虚警法计算量大的缺点,提出了一种根据检测舰船目标的特征,对每个可能的目标区域,快速计算检测阈值的方法。同时,研究了基于RNN网络及信噪比的特征选择方法,对目标的特征进行优选并对候选目标进行鉴别。实验结果表明,采用该方法进行舰船目标检测能获得较好的检测结果。

The effect of the traditional methods such as detection by a threshold or CFAR do not very well in ships detection form large scene and high resolution remote sensing images. To overcome these drawbacks, a method based on ship feature detection is proposed in this paper, which can compute threshold of every potential target with high speed. Besides, a meth- od of feature selection based on RNN algorithm and signal noise ratio is proposed, which can select good features of a target and identify ships from candidate detected targets. A number of experiments demonstrates good performance of the proposed method.