Please wait a minute...
 
国土资源遥感  2018, Vol. 30 Issue (2): 38-44    DOI: 10.6046/gtzyyg.2018.02.05
     技术方法 本期目录 | 过刊浏览 | 高级检索 |
利用局部稀疏不变特征的遥感影像检索
胡屹群(), 周绍光(), 岳顺, 刘晓晴
河海大学地球科学与工程学院,南京 211100
Remote sensing image retrieval based on sparse local invariant features
Yiqun HU(), Shaoguang ZHOU(), Shun YUE, Xiaoqing LIU
School of Earth Science and Engineering, Hohai University, Nanjing 211100, China
全文: PDF(3446 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

为了增强遥感影像局部特征的表征能力并充分利用过完备字典的稀疏分解,提出了基于稀疏表示特征构建视觉词典的遥感影像检索新方法。首先,提取遥感训练影像库的局部不变特征,对大量的局部特征训练过完备字典并将在该字典更新下获取的稀疏表示作为图像的特征描述; 然后,对稀疏表示特征构建视觉词典,并进行空间金字塔匹配,获取稀疏直方图特征; 最后,使用稀疏特征训练SVM分类模型,通过分类模型输出与查询影像属于一个类别的影像,在该类别的影像集中进行相似度匹配,返回与查询影像最为相似的图像,实现检索。实验结果表明,新方法提取的特征不仅具备局部不变特征的鲁棒性,还提供了必要的语义信息,在影像检索领域具有较强的实用性和适用性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
胡屹群
周绍光
岳顺
刘晓晴
关键词 局部不变特征过完备字典稀疏表示SVM分类模型影像检索    
Abstract

In order to enhance the capability of local feature representation of remote sensing images and to make full use of sparse decomposition of over-complete dictionary, this paper proposes a new method of remote sensing image retrieval based on sparse representation feature. In this method first the local invariant features are extracted from the training remote sensing image database and trains over-complete dictionary based on local features, and thus the sparse representation will be obtained under the dictionary update; the authors regard the sparse representation as the image’s final feature description. Secondly, the authors construct a visual dictionary using sparse representation features, and obtain the sparse histograms by spatial pyramid matching algorithm. Finally, the SVM classification model is trained based on the sparse features, by using the classification model, the images classified as one category with the query image to be output. The similarity matching is carried out in the output image set, and an image with the largest similarity is returned to achieve the image retrieval. Experimental result shows that the features extracted by the new method not only possess the robustness of local invariant features but also provide the necessary semantic information, which is of great practicality and applicability in image retrieval research field.

Key wordslocal invariant features    over-complete dictionary    sparse representation    SVM classification model    image retrieval
收稿日期: 2016-10-31      出版日期: 2018-05-30
:  P237  
基金资助:国家自然科学基金项目“高分辨率遥感影像中城市道路网的提取方法研究”(编号: 41271420/D010702)
通讯作者: 周绍光
引用本文:   
胡屹群, 周绍光, 岳顺, 刘晓晴. 利用局部稀疏不变特征的遥感影像检索[J]. 国土资源遥感, 2018, 30(2): 38-44.
Yiqun HU, Shaoguang ZHOU, Shun YUE, Xiaoqing LIU. Remote sensing image retrieval based on sparse local invariant features. Remote Sensing for Land & Resources, 2018, 30(2): 38-44.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2018.02.05      或      https://www.gtzyyg.com/CN/Y2018/V30/I2/38
Fig.1  基于局部稀疏不变特征的遥感影像检索系统
Fig.2  Merced Land Use Dataset遥感影像示例
Fig.3  本文方法的可视化结果
方法 平均精度 总体精度 Kappa
SIFT 0.623 6 0.592 7 0.579 3
纹理稀疏特征 0.845 5 0.827 0 0.818 3
本文方法 0.880 4 0.866 1 0.859 4
Tab.1  3种方法分类效果对比表
Fig.4  3种方法SVM分类效果对比
Fig.5  查准率-查全率曲线(平滑后的曲线)
类别 SIFT 纹理稀疏特征 本文方法
ANMRR 0.597 7 0.473 2 0.411 3
Tab.2  ANMRR值对比
[1] Du P J, Chen Y H, Tang H , et al.Study on content-based remote sensing image retrieval[C]//Proceedings of 2005 IEEE International Geoscience and Remote Sensing Symposium.Seoul:IEEE, 2005.
[2] 程起敏 . 遥感图像检索技术[M]. 武汉: 武汉大学出版社, 2011.
Cheng Q M. Remote Sensing Image Retrieval Technologies[M]. Wuhan: Wuhan University Press, 2011.
[3] Dos Santos J A,Penatti O A B,Torres R D S . Evaluating the Potential of Texture and Color Descriptors for Remote Sensing Image Retrieval and Classification[R].Technical Report-IC-09-47, 2009.
[4] Nandhini R, Joel T . Geographic image retrieval using local invariant features with euclidean distance[J]. IEEE International Journal for Research and Development in Engineering, 2014. 222-225.
[5] Lowe D G . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110.
doi: 10.1023/B:VISI.0000029664.99615.94
[6] 吴锐航, 李绍滋, 邹丰美 . 基于SIFT特征的图像检索[J]. 计算机应用研究, 2008,25(2):478-481.
doi: 10.3969/j.issn.1001-3695.2008.02.049
Wu R H, Li S Z, Zou F M . Image retrieval based on SIFT features[J]. Application Research of Computers, 2008,25(2):478-481.
[7] Yang Y, Newsam S . Geographic image retrieval using local invariant features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013,51(2):818-832.
doi: 10.1109/TGRS.2012.2205158
[8] Karakasis E G, Amanatiadis A, Gasteratos A , et al. Image moment invariants as local features for content based image retrieval using the bag-of-visual-words model[J]. Pattern Recognition Letters, 2015,55:22-27.
doi: 10.1016/j.patrec.2015.01.005
[9] 周维勋, 邵振峰, 侯继虎 . 利用视觉注意模型和局部特征的遥感影像检索方法[J]. 武汉大学学报(信息科学版), 2015,40(1):46-52.
doi: 10.13203/j.whugis20130130
Zhou W X, Shao Z F, Hou J H . Remote sensing imagery retrieval method based on visual attention model and local features[J]. Geomatics and Information Science of Wuhan University, 2015,40(1):46-52.
[10] Lazebnik S, Schmid C, Ponce J .Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories[C]//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York:IEEE, 2006: 2169-2178.
[11] Yang J C, Wright J, Huang T S , et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010,19(11):2861-2873.
doi: 10.1109/TIP.2010.2050625 pmid: 20483687
[12] Mohamadzadeh S, Farsi H . Content-based image retrieval system via sparse representation[J]. IET Computer Vision, 2016,10(1):95-102.
doi: 10.1049/iet-cvi.2015.0165
[13] Olshusen B A, Field D J . Sparse coding with an overcomplete basis set:A strategy employed by V1?[J]. Vision Research, 1997,37(23):3311-3325.
doi: 10.1016/S0042-6989(97)00169-7 pmid: 9425546
[14] Wright J, Ma Y, Mairal J , et al. Sparse representation for computer vision and pattern recognition[J]. Proceedings of the IEEE, 2010,98(6):1031-1044.
doi: 10.1109/JPROC.2010.2044470
[15] Aharon M, Elad M, Bruckstein A . K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Singal Processing, 2006,54(11):4311-4322.
doi: 10.1109/TSP.2006.881199
[16] 霍宏 . 生物视觉启发的高分辨率遥感影像特征提取与目标检测研究[D]. 上海:上海交通大学, 2014.
Huo H . Biological Vision-Inspired Feature Extraction and Object Detection for High Resolution Remote Sensing Images[D]. Shanghai:Shanghai Jiao Tong University, 2014.
[1] 任超锋, 蒲禹池, 张福强. 顾及地理空间信息的无人机影像匹配像对提取方法[J]. 自然资源遥感, 2022, 34(1): 85-92.
[2] 周光宇, 刘邦权, 张亶. 基于变分模态分解的SAR图像目标识别方法[J]. 国土资源遥感, 2020, 32(2): 33-39.
[3] 李成轶, 田淑芳. 基于字典学习的遥感影像超分辨率融合方法[J]. 国土资源遥感, 2017, 29(1): 50-56.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发