基于内容的卫星云图检索方法  

CBIR methods in satellite cloud image retrieval

作　　者：李艳兵[1] 李元祥[2] 黄思训[1] 翟景秋[3] 

机构地区：[1]解放军理工大学气象学院,江苏南京211101 [2]上海交通大学空天科学技术研究院,上海200030 [3]总参气象水文中心,北京100081

出　　处：《解放军理工大学学报（自然科学版）》2008年第2期130-136,共7页Journal of PLA University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(40575010)

摘　　要：为了有效地管理和利用大规模卫星云图数据库,需要为其增加检索功能,尤其是基于内容的检索。探讨了将基于内容的图像检索(CBIR)技术应用于卫星云图检索,选择使用了颜色、纹理和形状特征方法。颜色特征包括:灰度直方图和灰度聚合向量;纹理特征从小波子图提取,采用直方图拟合法和分块直方图拟合法;形状特征提取采用了新提出的一种专门针对云目标的"可变形模型"方法——圆形基元法。对每种特征定义了图像距离或者相似度,进行了检索比较实验。结果表明,CBIR用于卫星云图检索是可行的,形状特征方法因融入了领域知识而具有较突出的检索效果,但效率仍需提高。In order to efficiently manage and make use of large-scale satellite cloud image collections, it is useful and essential to build a database and to equip it with retrieval functions, especially content-based retrieval ones. Content-Based Image Retrieval （CBIR） techniques were applied to satellite cloud images. A series of methods were used to extract color, texture and shape features. Color features used were gray level histogram and gray level coherence vector. Texture features were extracted from wavelet subbands using two methods： histogram fitting which used parameters of generalized Gaussian density functions fitting subband histograms as features and partitioned histogram fitting method. Shape features were extracted using a new-proposed deformable model method aiming at cloud objects, called circle unit method. After image distance or similarity rules were given for each method, experiments were made. Results indicate that the application of CBIR in satellite cloud image retrieval is effective, and that specially designed shape method achieves much better performance than common methods due to the use of satellite cloud image domain knowledge, though at the same time more time-consuming.

关 键 词：基于内容的图像检索 形状特征 圆形基元法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]