基于视觉词袋模型的遥感图像分类方法  

Remote Sensing Image Classification with Bag-of-Visual-Words Model

作　　者：周宇谷 王平[1] 高颖慧[1] 

机构地区：[1]国防科学技术大学自动目标识别重点实验室,长沙410073

出　　处：《重庆理工大学学报（自然科学）》2015年第5期71-77,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(61103082)

摘　　要：研究了基于视觉词袋模型的单幅全色遥感图像的分类方法。首先提取图像边缘特征与图像区域,以旋转不变纹理基元作为视觉词汇,再采用面向对象方法进行分类。仿真结果表明:该方法具有较高的分类精度,且具有用时成本较低和适应性强的优点。The method of panchromatic remote sensing image classification based on bag-of-visual- words model was studied. Firstly, we extracted the feature of boundaries and the segments. Secondly, we used the rotation invariant texture feature as visual vocabulary. Finally, we applied the method of object-based for classification. The simulation results demonstrate that the proposed method has higher classification accuracy and has the advantages of low time-cost and stronz adaptability.

关 键 词：遥感图像 分类 视觉词袋模型 面向对象 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]