电子学报 ›› 2012, Vol. 40 ›› Issue (5): 911-919.DOI: 10.3969/j.issn.0372-2112.2012.05.009

• 学术论文 • 上一篇    下一篇

基于显著区域的月球影像内容特征研究

陈慧中1,2, 陈永光3, 景宁1, 陈荦1, 王钧1   

  1. 1. 国防科学技术大学电子科学与工程学院, 湖南长沙 410073;2. 西南电子电信技术研究所 上海分所, 上海 200434;3. 军械工程学院, 河北石家庄 050003
  • 收稿日期:2011-11-18 修回日期:2012-02-14 出版日期:2012-05-25
    • 基金资助:
    • 国家863高技术研究发展计划 (No.2008AA12A211,No.2011AA120300); 国家自然科学基金 (No.60902036,No.61070035)

Research of Content Feature Descriptors for Lunar Images Based on Saliency Regions

CHEN Hui-zhong1,2, CHEN Yong-guang3, JING Ning1, CHEN Luo1, WANG Jun1   

  1. 1. College of Electronic Science and Engineering, National University of Defense Technology, Changsha, Hunan 410073, China;2. Shanghai Branch, Southwest Electronic and Telecommunication Research Institution, Shanghai 200434, China;3. Ordnance Engineering College, Shijiazhuang, Hebei 050003, China
  • Received:2011-11-18 Revised:2012-02-14 Online:2012-05-25 Published:2012-05-25

摘要: 提出一种基于月球影像显著区域的内容特征(LIFBS),同时面向多核处理器架构,提出并行优化的LIFBS特征生成算法.该算法考虑显著子区域之间的方位、尺度、强度和距离关系,为每一个显著区域生成一个LIFBS局部特征,以此描述月球影像的内容.理论分析与实验结果表明,LIFBS特征具有良好的不变性与相似性表达,同时特征生成算法具有较高的并行效率.

关键词: 月球遥感影像, 基于内容的图像检索, 图像特征

Abstract: A feature descriptor called LIBFS is proposed for lunar remote sensing images based on the saliency regions and a parallel LIBFS generating algorithm is proposed facing the multi-cores processor architecture.The algorithm considers the location,scale,strength and distance relationship among different saliency regions in a lunar image.Several local LIBFS features are generated to describe the content of the image together.Theoretical analysis and experiments show that the LIBFS works well in invariance and similarity presentation,and the feature generating algorithm is of high parallel efficiency.

Key words: lunar remote sensing image, content-based image retrieval (CBIR), image feature

中图分类号: