一种改进包模型的遥感图像检索方法

杨进, 刘建波, 戴芹

杨进, 刘建波, 戴芹. 一种改进包模型的遥感图像检索方法[J]. 武汉大学学报 ( 信息科学版), 2014, 39(9): 1109-1113. DOI: 10.13203/j.whugis20130056
引用本文: 杨进, 刘建波, 戴芹. 一种改进包模型的遥感图像检索方法[J]. 武汉大学学报 ( 信息科学版), 2014, 39(9): 1109-1113. DOI: 10.13203/j.whugis20130056
YANG Jin, LIU Jianbo, DAI Qin. An Improved Remote Sensing Image Retrieval MethodBased on Bag of Word Framework[J]. Geomatics and Information Science of Wuhan University, 2014, 39(9): 1109-1113. DOI: 10.13203/j.whugis20130056
Citation: YANG Jin, LIU Jianbo, DAI Qin. An Improved Remote Sensing Image Retrieval MethodBased on Bag of Word Framework[J]. Geomatics and Information Science of Wuhan University, 2014, 39(9): 1109-1113. DOI: 10.13203/j.whugis20130056

一种改进包模型的遥感图像检索方法

详细信息
    作者简介:

    杨进,博士,副教授,主要从事遥感图像检索理论与方法研究。

  • 中图分类号: P237.4;TP753

An Improved Remote Sensing Image Retrieval MethodBased on Bag of Word Framework

More Information
    Author Bio:

    YANG Jin,PhD,associate professor,specializes in remote sensing image retrieval.

  • 摘要: 目的 提出了一种改进的包模型图像检索方法,使用本底图像构建视觉词汇字典。在建库过程中,通过近似KD-Tree搜索本底图像局部不变特征与入库图像特征间的对应匹配关系,并记录该关系;图像检索时,搜索检索图像与本底图像特征的对应关系,进而计算与入库图像的关系。该方法仅保存本底图像的局部不变特征,可实现感兴趣区域的图像检索。实验结果表明,该方法在提高图像检索准确性的同时,可以减少所需存储局部不变特征的数量。
    Abstract: Objective The Bag-of-Words(BoW)approach has lower retrieval accuracy performance for remotesensing image retrieval.The rate of correct results is very low especially when target textures are sim-ilar.To overcome this shortcoming,an indirect comparison between a query and target image basedon local invariant feature of the background image is proposed.The solution has two phases:theprocess of building a database and a retrieval process.After building a database,a search of the nea-rest neighbor feature in a query image in the feature space of the image dataset through an approximateKD-Tree is executed,then their relationship is recorded.The relationship can be used in calculatingsimilarity between a query and target image during a retrieval procedure.Experiments show that theproposed method has a better recognition performance than that of the BoW and,at the same time,needs less storage space for saving local invariant features.
  • [1] Mei Lixia,Tian Yumin.Region-Based Image Data-base Retrieval Method[J].Computer Engineering,2003,29(5):127-129(梅丽霞,田玉敏.基于区域的图像数据库检索方法[J],计算机工程,2003,29(5):127-129)[2] Molinier M,Laaksonen J,Hame T.DetectingMan-made Structures and Changes in Satellite Im-agery with a Content-Based Information RetrievalSystem Built on Self-organizing Maps[J].IEEETransactions on Geosciences and Remote Sensing,2007,45(4):861-874[3] Samal A,Bhatia S,Vadlamani P,et al.SearchingSatellite Imagery with Integrated Measures[J].Pattern Recognition,2009,42(11):2502-2513[4] Shyu C R,Klaric M,Scott G J,et al.GeoIRIS:Geospatial Information Retrieval and Indexing Sys-tem-content Mining,Semantics Modeling,andComplex Queries[J].IEEE Transactions on Geo-sciences and Remote Sensing,2007,45(4):839-852[5] Datcu M,Daschiel H,Pelizzari A,et al.Informa-tion Mining in Remote Sensing Image Archives:System Concepts[J].IEEE Transactions on Geosci-ences and Remote Sensing,2003,41(12):2923-2936[6] Sivic J,Zisserman A.Video Google:A Text Re-trieval Approach to Object Matching in Videos[C].The Ninth IEEE International Conference on Com-puter Vision,Washington D C,2003[7] Nister D,Stewenius H.Scalable Recognition with aVocabulary Tree[C].IEEE Computer Society Con-ference on Computer Vision and Pattern Recogni-1112 第39卷第9期 杨 进等:一种改进包模型的遥感图像检索方法tion,Washington D C,2006[8] Chum O,Philbin J,Sivic J,et al.Total Recall:Automatic Query Expansion with a Generative Fea-ture Model for Object Retrieval[C].IEEE 11th In-ternational Conference on Computer Vision,Wash-ington D C,2007[9] Lowe D.DistinctiveImage Features from Scale-in-variant Keypoints[J].International Journal ofComputer Vision,2004,60(2):91-110[10]Wan Xue,Zhang Zuxun,Ke Tao.An ImprovedSIFT Operator Based on the Theory of Zero-cross-ing on Feature Extraction[J].Geomatics and In-formation Science of Wuhan University,2013,38(3):270-273(万雪,张祖勋,柯涛.一种利用零交叉点理论的改进SIFT特征提取算法[J].武汉大学学报·信息科学版,2013,38(3):270-273)[11]Zhang Zuxun,Su Guozhong,Zhang Jianqing.Air-plane Pose Measurement from Image Sequences[J].Geomatics and Information Science of Wuhan Uni-versity,2004,29(4):287-291(张祖勋,苏国中,张剑清.基于序列影像的飞机姿态跟踪测量方法研究[J].武汉大学学报 · 信 息 科 学 版,2004,29(4):287-291)[12]Jegou H,Douze M,Schmid C.Hamming Embed-ding and Weak Geometric Consistency for LargeScale Image Search[C].European Conference onComputer Vision,France,2008
计量
  • 文章访问数:  1120
  • HTML全文浏览量:  48
  • PDF下载量:  577
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-04-17
  • 修回日期:  2014-09-04
  • 发布日期:  2014-09-04

目录

    /

    返回文章
    返回