A Novel Framework to Jointly Compress and Index Remote Sensing Images for Efficient Content-Based Retrieval

TL;DR

This paper introduces a joint framework that compresses and indexes remote sensing images simultaneously, enabling efficient content-based retrieval without the need for decoding, thus reducing computational costs in large-scale applications.

Contribution

It presents a novel auto-encoder based compression and hashing framework with a two-stage learning strategy for RS images, improving retrieval efficiency and accuracy.

Findings

Outperforms existing RS CBIR methods in accuracy

Reduces retrieval time by eliminating decoding step

Demonstrates effective compression and indexing in large-scale datasets

Abstract

Remote sensing (RS) images are usually stored in compressed format to reduce the storage size of the archives. Thus, existing content-based image retrieval (CBIR) systems in RS require decoding images before applying CBIR (which is computationally demanding in the case of large-scale CBIR problems). To address this problem, in this paper, we present a joint framework that simultaneously learns RS image compression and indexing. Thus, it eliminates the need for decoding RS images before applying CBIR. The proposed framework is made up of two modules. The first module compresses RS images based on an auto-encoder architecture. The second module produces hash codes with a high discrimination capability by employing soft pairwise, bit-balancing and classification loss functions. We also introduce a two stage learning strategy with gradient manipulation techniques to obtain image representations that are compatible with both RS image indexing and compression. Experimental results show the efficacy of the proposed framework when compared to widely used approaches in RS. The code of the proposed framework is available at https://git.tu-berlin.de/rsim/RS-JCIF.