基于多尺度Harris算法的海上舰船目标检测  

Shiptarget detection based on multi-scale Harris corner detection algorithm

作　　者：石桂名[1,2] 索继东[1] SHI Guiming;SUO Jidong(Information Science and Technology College,Dalian Maritime University,Dalian 116026,China;School of Electrical Engineering,Dalian University of Science and Technology,Dalian 116052,China)

机构地区：[1]大连海事大学信息科学与技术学院,辽宁大连116026 [2]大连科技学院电气工程学院,辽宁大连116052

出　　处：《电视技术》2018年第9期52-56,84,共6页Video Engineering

摘　　要：海上舰船目标的检测具有重要的研究意义和实用价值,而复杂多变的海面情况使得舰船目标的检测面临一定的困难。为了更加准确的检测舰船目标,本文提出了一种改进的多尺度Harris角点检测算法。首先利用改进的Canny算法求出舰船边缘信息;然后对原图像采用Mean-Shift滤波器滤除海杂波;最后设计不同半径的自适应圆形模板进行非极大值抑制,引入Laplace空间因子使得Harris角点检测算法具备多尺度特性,用该方法对舰船目标的角点进行检测。实验结果表明,本算文法舰船目标的角点分布均匀、定位精度高,同时具有尺度不变性和旋转不变性。Ship target detection has important research significance and utility value. It is difficult to get the ship target by the complex and changeable sea surface condition. In order to detect the ship targets more accurately, this article puts forward a new corner detection algorithm which based on improved Canny edge detection algorithm and improved multi - scale Harris corner detec- tion algorithm. First the edge information of the target can be got by the improved Canny algorithm. Then process the sea clutter in the original image by Mean - Shift filter. At last designs adaptive non - maximal suppression by Circle template with different radi- us, and phases in Laplace space factor, then adopts improved multi - scale Harris algorithm to detect the corners. According to the experimental results, the new method shows that the corners distribute equably and have high accuracy. At the same time combine scale invariance and rotational invariance.

关 键 词：舰船目标 HARRIS算法 角点检测 CANNY算法 Mean—Shift滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]