基于Top-hat变换与OTSU的近岸舰船目标检测

长期以来，雷达对近岸目标的检测是目标识别的难题。对于近岸低速舰船目标，存在探测难、识别难的问题。然而，舰船目标具有较好的红外辐射特征，在探测过程中可以充分地利用这一特征。针对其红外特性提出了一种基于Top-hat变换与最大类间方差法的图像处理方法。经开运算重构，利用Top-hat变换增强红外图像中目标与背景的对比度；根据图像的灰度特性，使用最大类间方差法对图像进行阈值分割，以便检测目标。实验结果表明，该算法能够有效地检测出近岸舰船目标，对近岸目标识别具有一定的现实意义。

In-shore Ship Target Detection Based on Top-hat Transformation and OTSU

Radar detection of in-shore targets has been a difficult problem in target recognition for a long time. It is difficult to detect and identify in-shore low-speed ship targets. However, ship targets have better infrared radiation characteristics which can be fully utilized in the detection process. According to these characteristics, an image processing method based on Top-hat transformation and OTSU is proposed. After open-operation reconstruction, the Top-hat transformation is used to enhance the contrast between the target and the background in an infrared image. To detect targets, the threshold values of the image are segmented by OTSU according to the gray-scale characteristics of the image. The experimental results show that the algorithm can effectively detect in-shore ship targets and is of a certain practical significance to the recognition of in-shore targets.