基于内容的遥感图像数据库植被区域检索

发布时间：2018-03-22 00:23

本文选题：遥感图像检索　切入点：植被区域　出处：《测绘与空间地理信息》2016年06期 　论文类型：期刊论文

【摘要】：随着遥感图像数量的急剧增加,基于内容的遥感图像检索系统已成为一个研究热点。该文在以综合区域匹配算法为图像相似度度量的前提下,提出了以空间绿颜色特征值降序排序的遥感图像数据库植被区域检索方法。首先,用综合区域匹配算法对图像进行相似度度量;然后,依据这些图像的空间绿颜色特征值对图像进行降序排序,从而得到含有植被区域这一高级语义特征的检索结果。实验表明:该方法将检索查准率提高了20%,检索效率明显提高,可满足用户的需求。
[Abstract]:With the rapid increase in the number of remote sensing images, content-based remote sensing image retrieval system has become a research hotspot. This paper presents a method of vegetation region retrieval in remote sensing image database based on descending order of spatial green color eigenvalues. Firstly, the synthetic region matching algorithm is used to measure the similarity of images. According to the spatial green color characteristic value of these images, the image is sorted in descending order, and the retrieval result with the high-level semantic feature of vegetation region is obtained. The experimental results show that the retrieval accuracy rate is increased by 20%, and the retrieval efficiency is obviously improved by this method. Can meet the needs of users.
【作者单位】：兰州交通大学测绘与地理信息学院;甘肃省地理国情监测工程实验室;
【基金】：甘肃省高等学校基本科研业务费项目——基于空间关系敏感的高分辨率卫星图像检索技术研究(213049)资助
【分类号】：P237

【相似文献】