Special Issue "Content-Based Remote Sensing Image Retrieval"

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: closed (30 June 2020).

Special Issue Editors

Dr. Miguel A. Veganzones
Website
Guest Editor
AI Director in Sherpa.ai and Lecturer in Deusto University's Big Data and Business Intelligence Posgrade Program , Astigarraga, Basque Country, Spain
Interests: machine learning; image processing; pattern recognition; classification supervised learning; feature extraction; computational intelligence; artificial intelligence; statistics; remote sensing
Prof. Mihai Datcu
Website
Guest Editor
German Aerospace Center (DLR), Remote Sensing Technology Institute, Oberpfaffenhofen, 82234 Weßling, Germany
Interests: signal processing; information theory; big data mining; VHR SAR; deep learning
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

During the last decade we have witnessed an exponential growth in the data collection interest all around every aspect of our lives. The technological requirements demanded to effectively analyze such rapid accumulation of vast amounts of data has yield to the development of novel distributed systems to support the management of such big data infrastructures. This has naturally lead to a bloom of data-analysis methods developments, particularly in the machine learning field.

The Remote Sensing community has been also actively involved in this new paradigm. High performance sensors has led to an ever-increasing of public and private geospatial repositories. Not only the massiveness of remote sensing data volumes presents a challenge for the Remote Sensing community, the complexity of said data has also flourished with the diversity of sensors resolutions (satellites, airbornes, drones), spectral capacities (LIDAR, SAR, polSAR, multi-, hyper- and ultra-spectral), image acquisition procedures (images, tiles, video sequences) and a large body of applications of interest (Earth Observation, planetology, astronomy, precision agriculture, crisis management, etc.).

The Image Analysis and Image Retrieval communities have taken great advantage of this new scenario and have benefited from both, the availability of huge amounts of data and the development of new techniques, e.g., deep learning models. Still, remote sensing data is a particularly challenging domain for the design and development of effective general-purpose retrieval systems:

* Data representations capable of handling multi-modality (particularly across different spatial and spectral resolutions).

* Effective user-oriented interfaces for querying and feedback management.

* Models to exploit heterogeneous and application-dependent user communities prior information.

* Standards for the deployment of big unstructured remote sensing data warehouses and scalable infrastructures.

* Scarcity of public benchmarks with reliable ground-truth and annotated images.

* Generative models to synthetize spatially and spectrally realistic remote sensing images.

* Models for real time interactive analysis and characterization of multi-modal remote sensing data.

* Exploitation of complementary data from the Internet of Things, i.e., smartphone sensors, portable measurement devices, wearables, etc.

The purpose of this Special Issue is to highlight the urgent necessity of delivering novel remote sensing image retrieval systems that could effectively extract valuable information from a variety of remote sensing data sources and could match the diverse needs of the increasing variety of scientific and industrial applications demanded by practitioners.

Topics of interest:

* Content- and context-based indexing, search and retrieval of RS data

* Search and browsing on RS big data repositories to face the Peta/Zettabyte scale

* Advanced descriptors and similarity metrics dedicated to multi-modal RS data

* Usage of prior knowledge and semantic information for retrieval in RS

* Matching learning for image retrieval in remote sensing

* Query models, paradigms, and languages dedicated to RS

* Multimodal/multi-observations (sensors, dates, resolutions) analysis of RS data

* HCI issues in RS retrieval and browsing

* Evaluation of RS retrieval systems

* Dissemination of publicly available RS groundtruth and annotated images

* RS image generative processes

* High performance indexing algorithms for RS data

* Real-time information retrieval techniques and applications

* Summarization and visualization of very large satellite image datasets

* Applications of image retrieval in remote sensing

* Models and applications of RD data and IoT data hybrid approaches

Dr. Miguel A. Veganzones

Prof. Mihai Datcu

 


Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Image retrieval systems
  • Multi-modality
  • Big data architectures
  • Earth Observation
  • Remote Sensing data visualization
  • Remote Sensing data analysis
  • Image descriptors
  • Semantic analysis
  • Image annotation
  • Image generative processes

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling
Remote Sens. 2020, 12(17), 2789; https://doi.org/10.3390/rs12172789 - 27 Aug 2020
Abstract
As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows the retrieval time and [...] Read more.
As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows the retrieval time and takes up a great deal of memory space. The hash method is being increasingly used for rapid image retrieval because of its remarkably fast performance. At the same time, selecting samples that contain more information and greater stability to train the network has gradually become the key to improving retrieval performance. Given the above considerations, we propose a deep hash remote sensing image retrieval method, called the hard probability sampling hash retrieval method (HPSH), which combines hash code learning with hard probability sampling in a deep network. Specifically, we used a probability sampling method to select training samples, and we designed one novel hash loss function to better train the network parameters and reduce the hashing accuracy loss due to quantization. Our experimental results demonstrate that HPSH could yield an excellent representation compared with other state-of-the-art hash approaches. For the university of California, merced (UCMD) dataset, HPSH+S resulted in a mean average precision (mAP) of up to 90.9% on 16 hash bits, 92.2% on 24 hash bits, and 92.8% on 32 hash bits. For the aerial image dataset (AID), HPSH+S achieved a mAP of up to 89.8% on 16 hash bits, 93.6% on 24 hash bits, and 95.5% on 32 hash bits. For the UCMD dataset, with the use of data augmentation, our proposed approach achieved a mAP of up to 99.6% on 32 hash bits and 99.7% on 64 hash bits. Full article
(This article belongs to the Special Issue Content-Based Remote Sensing Image Retrieval)
Show Figures

Figure 1

Open AccessArticle
Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval
Remote Sens. 2020, 12(1), 175; https://doi.org/10.3390/rs12010175 - 03 Jan 2020
Cited by 4
Abstract
Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures [...] Read more.
Remote sensing images are featured by massiveness, diversity and complexity. These features put forward higher requirements for the speed and accuracy of remote sensing image retrieval. The extraction method plays a key role in retrieving remote sensing images. Deep metric learning (DML) captures the semantic similarity information between data points by learning embedding in vector space. However, due to the uneven distribution of sample data in remote sensing image datasets, the pair-based loss currently used in DML is not suitable. To improve this, we propose a novel distribution consistency loss to solve this problem. First, we define a new way to mine samples by selecting five in-class hard samples and five inter-class hard samples to form an informative set. This method can make the network extract more useful information in a short time. Secondly, in order to avoid inaccurate feature extraction due to sample imbalance, we assign dynamic weight to the positive samples according to the ratio of the number of hard samples and easy samples in the class, and name the loss caused by the positive sample as the sample balance loss. We combine the sample balance of the positive samples with the ranking consistency of the negative samples to form our distribution consistency loss. Finally, we built an end-to-end fine-tuning network suitable for remote sensing image retrieval. We display comprehensive experimental results drawing on three remote sensing image datasets that are publicly available and show that our method achieves the state-of-the-art performance. Full article
(This article belongs to the Special Issue Content-Based Remote Sensing Image Retrieval)
Show Figures

Graphical abstract

Open AccessArticle
A Deep Hashing Technique for Remote Sensing Image-Sound Retrieval
Remote Sens. 2020, 12(1), 84; https://doi.org/10.3390/rs12010084 - 25 Dec 2019
Cited by 2
Abstract
With the rapid progress of remote sensing (RS) observation technologies, cross-modal RS image-sound retrieval has attracted some attention in recent years. However, these methods perform cross-modal image-sound retrieval by leveraging high-dimensional real-valued features, which can require more storage than low-dimensional binary features (i.e., [...] Read more.
With the rapid progress of remote sensing (RS) observation technologies, cross-modal RS image-sound retrieval has attracted some attention in recent years. However, these methods perform cross-modal image-sound retrieval by leveraging high-dimensional real-valued features, which can require more storage than low-dimensional binary features (i.e., hash codes). Moreover, these methods cannot directly encode relative semantic similarity relationships. To tackle these issues, we propose a new, deep, cross-modal RS image-sound hashing approach, called deep triplet-based hashing (DTBH), to integrate hash code learning and relative semantic similarity relationship learning into an end-to-end network. Specially, the proposed DTBH method designs a triplet selection strategy to select effective triplets. Moreover, in order to encode relative semantic similarity relationships, we propose the objective function, which makes sure that that the anchor images are more similar to the positive sounds than the negative sounds. In addition, a triplet regularized loss term leverages approximate l1-norm of hash-like codes and hash codes and can effectively reduce the information loss between hash-like codes and hash codes. Extensive experimental results showed that the DTBH method could achieve a superior performance to other state-of-the-art cross-modal image-sound retrieval methods. For a sound query RS image task, the proposed approach achieved a mean average precision (mAP) of up to 60.13% on the UCM dataset, 87.49% on the Sydney dataset, and 22.72% on the RSICD dataset. For RS image query sound task, the proposed approach achieved a mAP of 64.27% on the UCM dataset, 92.45% on the Sydney dataset, and 23.46% on the RSICD dataset. Future work will focus on how to consider the balance property of hash codes to improve image-sound retrieval performance. Full article
(This article belongs to the Special Issue Content-Based Remote Sensing Image Retrieval)
Show Figures

Figure 1

Open AccessArticle
Large-Scale Remote Sensing Image Retrieval Based on Semi-Supervised Adversarial Hashing
Remote Sens. 2019, 11(17), 2055; https://doi.org/10.3390/rs11172055 - 01 Sep 2019
Cited by 5
Abstract
Remote sensing image retrieval (RSIR), a superior content organization technique, plays an important role in the remote sensing (RS) community. With the number of RS images increases explosively, not only the retrieval precision but also the retrieval efficiency is emphasized in the large-scale [...] Read more.
Remote sensing image retrieval (RSIR), a superior content organization technique, plays an important role in the remote sensing (RS) community. With the number of RS images increases explosively, not only the retrieval precision but also the retrieval efficiency is emphasized in the large-scale RSIR scenario. Therefore, the approximate nearest neighborhood (ANN) search attracts the researchers’ attention increasingly. In this paper, we propose a new hash learning method, named semi-supervised deep adversarial hashing (SDAH), to accomplish the ANN for the large-scale RSIR task. The assumption of our model is that the RS images have been represented by the proper visual features. First, a residual auto-encoder (RAE) is developed to generate the class variable and hash code. Second, two multi-layer networks are constructed to regularize the obtained latent vectors using the prior distribution. These two modules mentioned are integrated under the generator adversarial framework. Through the minimax learning, the class variable would be a one-hot-like vector while the hash code would be the binary-like vector. Finally, a specific hashing function is formulated to enhance the quality of the generated hash code. The effectiveness of the hash codes learned by our SDAH model was proved by the positive experimental results counted on three public RS image archives. Compared with the existing hash learning methods, the proposed method reaches improved performance. Full article
(This article belongs to the Special Issue Content-Based Remote Sensing Image Retrieval)
Show Figures

Graphical abstract

Back to TopTop