基于SRM分割和分层线段特征的船舶目标检测方法

Ship target detection method based on SRM segmentation and hierarchical line segment features

针对高分辨率遥感图像细节丰富、纹理复杂,分析困难的问题,且船舶长宽比特征是一个很重要的特征,提出一种基于SRM分割和分层线段特征提取的船舶目标检测方法.利用分层线段搜索更新以及合并附近在阈值下的线段进行快速检测船舶目标.实验结果表明,该检测方法能够有效地检测出高分辨率遥感图像的船舶目标,不需要太多的参数和训练样本,且采用分层线段特征提取方法的性能优于其他常用方法.

In this paper,a ship target detection method based on SRM segmentation and hierarchical line segment feature extraction is proposed for high resolution remote sensing images.Because of the rich details and complex texture of high resolution remote sensing images,it is difficult to analyze them.The ship′s length-width ratio is an important feature.Based on line segment extraction,the ship′s target can be quickly detected by searching and updating the layered line segments and merging the adjacent line segments under the threshold.The experimental results show that the proposed method can effectively detect ship targets in high-resolution remote sensing images,and the performance of the hierarchical line segment feature extraction method is better than other commonly used methods.At the same time,the ship detection method in this paper does not need too many parameters and training samples.