面向查询点的遥感影像哈希检索方法  

Query point-oriented Hashing retrieval of remote sensing images

作　　者：陈诚[1] 邹焕新[1] 邵宁远 孙嘉赤 秦先祥[2] CHEN Cheng;ZOU Huanxin;SHAO Ningyuan;SUN Jiachi;QIN Xianxiang(College of Electronic Science and Technology,National University of DefenseTechnology,Changsha 410073,China;Information and Navigation College,Air Force Engineering University,Xi’an 710077,China)

机构地区：[1]国防科技大学电子科学学院,湖南长沙410073 [2]空军工程大学信息与导航学院,陕西西安710077

出　　处：《系统工程与电子技术》2019年第8期1713-1719,共7页Systems Engineering and Electronics

基　　金：国家自然科学基金(41601436,61331015)资助课题

摘　　要：由于存储成本低,查询速度快,哈希检索算法已被广泛应用于大规模影像检索。针对大规模遥感影像数据集训练低效问题,提出了面向查询点进行特征学习的遥感影像检索方法。首先,利用深度卷积网络对具有多语义标签的遥感影像数据训练集提取遥感影像特征;然后,面向查询点学习得到哈希函数并生成查询点的二进制哈希码;最后,通过迭代学习得到整个数据库的二进制哈希码来实现影像检索,有利于提高检索精度;同时,该方法避免了对整个数据库进行特征提取,从而可以更有效地利用大规模数据库中的监督信息。在3个不同数据集上的实验结果表明,该方法检索性能优于其他多种先进方法。Due to the low storage cost and fast query speed,the Hashing retrieval algorithm has been widely used for large-scale image retrieval.Aiming at the inefficiency of large-scale remote sensing image dataset trai-ning,a remote sensing image retrieval method based on query points for feature learning is proposed.First,the image features are extracted from the remote sensing image data training set with multiple semantic tags by using the deep convolutional network.Then,the Hashing function is learned from the query points and the Hashing codes of the query points are generated by using the learned Hashing function,and finally the binary Hashing codes of the whole image database are obtained through iterative learning,which is helpful to improve the retrieval accuracy.The feature extraction of the entire database is avoided in the process of image retrieval,and thus the supervised information in the large-scale database is more effectively utilized for image retrieval.Extensive experimental results conducted on three different datasets demonstrate that the performance of the proposed method is better than those of several other state-of-the-art approaches.

关 键 词：影像检索 遥感影像 深度学习 哈希 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]