南京理工大学学报（自然科学版）2024，Vol.48Issue(4)：434-441,8.DOI:10.14177/j.cnki.32-1397n.2024.48.04.004
基于深度旋转不变特征图哈希的遥感图像检索
Deep rotation-invariant feature map hash for remote sensing image retrieval
摘要
Abstract
Hash generates compact hash code for data representation,and is widely used for large-scale remote sensing image retrieval due to its efficiency.Affected by satellite observations,the same object may appear at multiple angles in different remote sensing images which leads to decline of retrieval performance.To address this issue,this paper proposes deep rotation-invariant feature map hash,i.e.,DRIFMH,including feature map extraction and hash quantization modules.The feature extraction module rotates the feature map at different angles,proposes a feature consistency loss,and maintains the consistency of image features at different rotation angles,overcoming the adverse effects of rotation.The hash quantization module performs binary quantization on image features to generate hash codes,and introduces classification cross entropy loss to enhance the discriminative ability of the hash codes.The proposed method is evaluated on AID and UCMD datasets and compared with multiple hash methods in experiments,and the empirical results demonstrate that the proposed DRIFMH can generate rotation-invariant remote sensing image feature and improve the performance of large-scale remote sensing image retrieval.关键词
遥感图像检索/哈希/特征图/旋转不变性Key words
remote sensing image retrieval/hash/feature map/rotation-invariance分类
信息技术与安全科学引用本文复制引用
胡明浩,张博文,沈肖波,孙权森..基于深度旋转不变特征图哈希的遥感图像检索[J].南京理工大学学报（自然科学版）,2024,48(4):434-441,8.基金项目
国家自然科学基金(62176126) （62176126）
江苏省自然科学基金(BK20230095) （BK20230095）
中央高校基本科研业务费专项资金(30921011210) （30921011210）
