Abstract
Remote sensing image retrieval (RSIR) is one of the most challenging tasks in remote sensing (RS) community. With the volume of RS images increases explosively, conventional exhaustive search is often infeasible in real applications. Recently, hashing has attracted increasing attention for RSIR due to significant advantage in terms of computation and storage. Hashing first generates a set of short compact hash codes to encode RS images, and then applies hash codes for effective RSIR. Multiview hashing usually achieves promising RSIR performance by fusing multiples kinds of RS image features. Conventional multiview hashing simply predefines graph Laplacian in each view, which cannot effectively explore underlying similarity structures among RS images. To address this issue, this article proposes a novel multiview inherent graph hashing (MvIGH) for RSIR. MvIGH captures the latent similarities among RS images, and adaptively learns weights of each view to characterize its contribution. In addition, MvIGH further minimizes the quantization errors. We develop an efficient alternating algorithm to solve the formulated optimization problem. The experiments on three public RS image datasets demonstrate the superiority of the proposed method over the existing multiview hashing methods in RSIR tasks.
Highlights
W ITH the rapid development of earth observation (EO), the volume of remote sensing (RS) data increases dramatically [1]–[3]
The results demonstrate that the proposed multiview inherent graph hashing (MvIGH) outperforms the state-of-the-art multiview hashing methods in remote sensing image retrieval (RSIR)
The proposed MvIGH adaptively learns the weights of the multiple views to capture the latent similarity structures among RS images
Summary
W ITH the rapid development of earth observation (EO), the volume of remote sensing (RS) data increases dramatically [1]–[3]. The data-dependent methods [9]–[19], which are called learning to hash methods, have recently been proposed to address this problem They apply machine learning techniques to learn the hash functions from the training set to generate more compact binary codes. How to generate high-quality hash codes that capture the inherent similarity structure from multiview data is still a challenging research topic. Due to the effectiveness of hashing-based methods, in this article, we introduced a new multiview hashing method to address the above challenges for RSIR task This method adaptively learns the weights among the nearest neighbors to fully capture the latent similarity structure among the multiple views. MvIGH jointly learns the hash codes, hash functions and adaptive similarity weights within one framework to fully preserve the latent similarity structure of multiview RS data.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
