基于纹理特征驱动AdaBoost算法的海面场景分类  

Sea scene classification based on Ada Boost algorithm with texture characteristics

作　　者：戴军[1] 金代中[1] 高志峰[1] 

机构地区：[1]西南技术物理研究所,四川成都610041

出　　处：《激光与红外》2015年第4期462-466,共5页Laser & Infrared

摘　　要：为提高红外成像系统对场景的感知能力,对海面场景分类进行了研究,提出了一种基于纹理特征驱动Ada Boost算法的海面场景分类方法。该方法首先提取图像的纹理特征,然后引入Ada Boost算法进行最优特征选择,构建强分类器,最后通过二叉树结构实现对海面场景的多分类。实验结果表明:该方法适应能力强,对多种复杂的海面场景分类效果好。分类结果可为目标检测算法的选取以及复合制导的综合决策提供依据。To improve the sea scene perception of IR image system,a sea scene classification method based on AdaBoost algorithm with texture characteristics is proposed. Firstly,texture characteristics of the images are extracted.Then Ada Boost algorithm is introduced to select the best characteristic,and the stronger classifier is designed. Finally,sea scene classification is realized through binary tree structure. The experimental results show that the method has good adaptive capacity and can obtain classification results under various complicated sea scenes. The classification results will provide important experimental basis for selection of target detection algorithms.

关 键 词：ADABOOST算法 Laws纹理 灰度共生矩阵 红外图像处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]