海上舰船目标轮廓检测算法

Target contour detection algorithm for marine ships

利用高分辨率光学遥感图像对海上舰船进行监控,具有广阔的应用前景。针对舰船轮廓检测时易受干扰,且对噪声敏感的问题,为了更精确地检测舰船轮廓,以关键点描述方法理论为基础,提出了新的关键点检测方法。基于灰度信息提取出舰船目标区域,结合灰度和形状信息,提取出对称点对来检测关键点,对舰船轮廓拟合效果较好。该船只轮廓检测算法结合舰船灰度特征和形状特征,适用于多种船形和场景,轮廓检测效果良好,鲁棒性强。

Using high-resolution optical remote sensing images to monitor marine ships has broad application prospects.Aiming at the problem that ship contour detection is easy to be disturbed and sensitive to noise,in order to detect ship contour more accurately,a new key point detection method is proposed based on the theory of key point description method.Ship target area is extracted based on grey information.Combined with grey and shape information,symmetrical point pairs are extracted to detect key points.The method has a good effect on ship contour fitting.The ship contour detection algorithm combines ship grey features and shape features.It is suitable for a variety of ship shapes and scenes.The contour detection effect is good and robust.