一种基于可变夹角链码的靠岸舰船目标检测方法

An AIAC-based Inshore Ship Target Detection Approach

高分辨率遥感图像上靠岸舰船的灰度、纹理特征往往和码头接近,其自动检测相对比较困难,而半米粒状轮廓特征是靠岸舰船检测中区分度较好的特征之一。利用可变夹角链码对靠岸舰船的这种轮廓特征进行描述,具有平移、旋转及缩放相对不变性。改进了可变夹角链码生成算法,并在此基础上提出了一种基于可变夹角链码的靠岸舰船检测方法。实测数据实验证明该方法在一定程度上能够解决靠岸舰船检测问题。

In high spatial resolution sensing image, it was hard to discriminate inshore ships from harbors because of the similarity of gray and texture for both targets. The half ellipse shape of the inshore ship in the contour, was one of the features with better distinguish ability. An alterable included angle chain （AIAC）-based curve description was introduced to describe the inchore ship contours in this paper, which was invariant to rotation, scaling and translation. In the following an improved AIAC generation method was presented. Finally an AIAC-based inshore ship detection approach was proposed by describing and matching the counter feature of inshore ship by AIAC. Experiments based on the satellite sensing image demonstrated that the algorithm proposed could solve the inshore ship detection problem in a certain extent.