舰船分类的PHOG和支持向量机联合检测方法  

Combined Detection Method of PHOG and SVM for Ship Classification

作　　者：翟玉婷[1] 郑智林[1] 苑志江[1] ZHAI Yu - ting ZHENG Zhi - lin YUAN Zhi - jiang(Department of Navigation, Dalian Naval Academy, Dalian Liaoling 116018, China)

机构地区：[1]海军大连舰艇学院,辽宁大连116018

出　　处：《计算机仿真》2017年第6期431-434,439,共5页Computer Simulation

基　　金：舰船流场特性测量技术研究(DJYKYKT2016-05)

摘　　要：针对普通舰船分类检测方法容易受到物理噪声干扰、实时性差等问题,采用塔式边缘方向梯度直方图和支持向量机联合检测方法对不同类别水面舰船图像进行实时分类检测。通过对不同类别舰船图像进行分类实验,进一步综合确定适合的图像特征参数及核函数参数,实验结果表明,舰船分类检测准确率较现有检测方法有所提高。基于塔式边缘方向梯度直方图和支持向量机的联合检测方法能够实现实时、可靠的舰船分类检测。For the problems in general ship classification detection method, such as susceptible to physical noise, poor real - time and so on, a combined detection method of PHOG and SVM is used to classify the images of different types of surface ships in real time. The appropriate parameters of the image feature and kernel function are analyzed and determined through the classification of different types of images of ships experiments. The experiments show that the accuracy of ship classification is improved compared with the existing detection methods, and the combined detection method based on PHOG and SVM can achieve real - time and reliable detection of ship classification.

关 键 词：舰船分类 支持向量机 塔式边缘方向梯度直方图 核函数 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]