? 基于深度跨域特征的遥感影像检索
Journal of Computer Science and Technology
Quick Search in JCST
 Advanced Search 
      Home | PrePrint | SiteMap | Contact Us | Help
 
Indexed by   SCIE, EI ...
Bimonthly    Since 1986
Journal of Computer Science and Technology 2017, Vol. 32 Issue (4) :726-737    DOI: 10.1007/s11390-017-1754-7
Special Issue on Deep Learning << Previous Articles | Next Articles >>
基于深度跨域特征的遥感影像检索
Tian-Bi Jiang1,2, Gui-Song Xia1, Senior Member, IEEE, Member, CCF,Qi-Kai Lu2,*, Wei-Ming Shen1
1 State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University Wuhan 430079, China;
2 School of Electronic Information, Wuhan University, Wuhan 430072, China
Retrieving Aerial Scene Images with Learned Deep Image-Sketch Features
Tian-Bi Jiang1,2, Gui-Song Xia1, Senior Member, IEEE, Member, CCF,Qi-Kai Lu2,*, Wei-Ming Shen1
1 State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University Wuhan 430079, China;
2 School of Electronic Information, Wuhan University, Wuhan 430072, China

摘要
参考文献
相关文章
Download: [PDF 5756KB]  
摘要 由于当前遥感影像检索系统在缺少待检索影像时难以正常发挥作用,因此,本研究基于手绘草图完成遥感影像检索。遥感影像地物结构复杂、空间分辨率多样,利用简单的手绘草图检索复杂的遥感影像是一项非常具有挑战性的任务。本文首次提出一种获取跨域特征的方法用于实现基于草图检索遥感影像的目标。首先,我们收集了包括遥感影像和手绘草图的数据集,并对其进行多尺度数据增强,在此基础上训练多细节尺度的深度学习模型,使用深度网络的全连接层作为跨域特征用以描述图像和草图,最后采用草图和图像特征之间的欧式距离来衡量两者的相似度并排序,获得检索结果。在多个公共遥感影像数据集上的实验证实了本文提出的方法明显优于传统的方法。
关键词草图   遥感影像检索   多尺度   深度跨域模型     
Abstract: This paper investigates the problem of retrieving aerial scene images by using semantic sketches, since the state-of-the-art retrieval systems turn out to be invalid when there is no exemplar query aerial image available. However, due to the complex surface structures and huge variations of resolutions of aerial images, it is very challenging to retrieve aerial images with sketches and few studies have been devoted to this task. In this article, for the first time to our knowledge, we propose a framework to bridge the gap between sketches and aerial images. First, an aerial sketch-image database is collected, and the images and sketches it contains are augmented to various levels of details. We then train a multi-scale deep model by the new dataset. The fully-connected layers of the network in each scale are finally connected and used as cross-domain features, and the Euclidean distance is used to measure the cross-domain similarity between aerial images and sketches. Experiments on several commonly used aerial image datasets demonstrate the superiority of the proposed method compared with the traditional approaches.
Keywordssketch   aerial image retrieval   multi scale   deep cross-domain model     
Received 2016-12-20;
本文基金:

This work was supported by the National Natural Science Foundation of China under Grant Nos. 41501462 and 91338113.

通讯作者: Qi-Kai Lu     Email: qikai_lu@whu.edu.cn
About author: Tian-Bi Jiang received her B.S. degree in remote sensing science and technology from Wuhan University, Wuhan, in 2015. She is currently pursuing her M.S. degree in photogrammetry and remote sensing with the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan. Her current research mainly focuses on sketch-based image retrieval and image understanding.
引用本文:   
Tian-Bi Jiang, Gui-Song Xia, Qi-Kai Lu, Wei-Ming Shen.基于深度跨域特征的遥感影像检索[J]  Journal of Computer Science and Technology , 2017,V32(4): 726-737
Tian-Bi Jiang, Gui-Song Xia, Qi-Kai Lu, Wei-Ming Shen.Retrieving Aerial Scene Images with Learned Deep Image-Sketch Features[J]  Journal of Computer Science and Technology, 2017,V32(4): 726-737
链接本文:  
http://jcst.ict.ac.cn:8080/jcst/CN/10.1007/s11390-017-1754-7
Copyright 2010 by Journal of Computer Science and Technology