FG Remote Sensing Image Analysis Group

26 Items

Recent Submissions
Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification

Roy, Subhankar ; Sangineto, Enver ; Demir, Begüm ; Sebe, Nicu (2018-09-06)

Most of the public satellite image datasets contain only a small number of annotated images. The lack of a sufficient quantity of labeled data for training is a bottleneck for the use of modern deep-learning based classification approaches in this domain. In this paper we propose a semi -supervised approach to deal with this problem. We use the discriminator (D) of a Generative Adversarial Netw...

A Progressive Content-Based Image Retrieval in JPEG 2000 Compressed Remote Sensing Archives

Preethy Byju, Akshara ; Demir, Begüm ; Bruzzone, Lorenzo (2020-02-24)

Due to the dramatically increased volume of remote sensing (RS) image archives, images are usually stored in a compressed format to reduce the storage size. Existing content-based RS image retrieval (CBIR) systems require as input fully decoded images, thus resulting in a computationally demanding task in the case of large-scale CBIR problems. To overcome this limitation, in this article, we pr...

High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery

Kang, Jian ; Fernández-Beltrán, Rubén ; Ye, Zhen ; Tong, Xiaohua ; Ghamisi, Pedram ; Plaza, Antonio (2020-08-12)

Deep metric learning has recently received special attention in the field of remote sensing (RS) scene characterization, owing to its prominent capabilities for modeling distances among RS images based on their semantic information. Most of the existing deep metric learning methods exploit pairwise and triplet losses to learn the feature embeddings with the preservation of semantic-similarity, ...

Robust Fine Registration of Multisensor Remote Sensing Images Based on Enhanced Subpixel Phase Correlation

Ye, Zhen ; Kang, Jian ; Yao, Jing ; Song, Wenping ; Liu, Sicong ; Luo, Xin ; Xu, Yusheng ; Tong, Xiaohua (2020-08-04)

Automatic fine registration of multisensor images plays an essential role in many remote sensing applications. However, it is always a challenging task due to significant radiometric and textural differences. In this paper, an enhanced subpixel phase correlation method is proposed, which embeds phase congruency-based structural representation, L1-norm-based rank-one matrix approximation with ad...

An Approach To Super-Resolution Of Sentinel-2 Images Based On Generative Adversarial Networks

Zhang, Kexin ; Sumbul, Gencer ; Demir, Begüm (2020-06-02)

This paper presents a generative adversarial network based super-resolution (SR) approach (which is called as S2GAN) to enhance the spatial resolution of Sentinel-2 spectral bands. The proposed approach consists of two main steps. The first step aims to increase the spatial resolution of the bands with 20m and 60m spatial resolutions by the scaling factors of 2 and 6, respectively. To this end,...

Unsupervised Remote Sensing Image Retrieval Using Probabilistic Latent Semantic Hashing

Fernandez-Beltran, Ruben ; Demir, Begüm ; Pla, Filiberto ; Plaza, Antonio (2020-02-06)

Unsupervised hashing methods have attracted considerable attention in large-scale remote sensing (RS) image retrieval, due to their capability for massive data processing with significantly reduced storage and computation. Although existing unsupervised hashing methods are suitable for operational applications, they exhibit limitations when accurately modeling the complex semantic content prese...

SD-RSIC: Summarization-Driven Deep Remote Sensing Image Captioning

Sumbul, Gencer ; Nayak, Sonali ; Demir, Begüm (2020-10-26)

Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN-based approaches rely on the availability of a training set made up of a high number of RS images with their captions. However, captions of training images may contain redundant information (they can be repetitive or semantically similar to each other), resulting in in...

Remote-Sensing Image Scene Classification With Deep Neural Networks in JPEG 2000 Compressed Domain

Preethy Byju, Akshara ; Sumbul, Gencer ; Demir, Begüm ; Bruzzone, Lorenzo (2020-07-20)

To reduce the storage requirements, remote-sensing (RS) images are usually stored in compressed format. Existing scene classification approaches using deep neural networks (DNNs) require to fully decompress the images, which is a computationally demanding task in operational applications. To address this issue, in this article, we propose a novel approach to achieve scene classification in Join...

Toward Remote Sensing Image Retrieval Under a Deep Image Captioning Perspective

Hoxha, Genc ; Melgani, Farid ; Demir, Begüm (2020-08-03)

The performance of remote sensing image retrieval (RSIR) systems depends on the capability of the extracted features in characterizing the semantic content of images. Existing RSIR systems describe images by visual descriptors that model the primitives (such as different land-cover classes) present in the images. However, the visual descriptors may not be sufficient to describe the high-level c...

Component Decomposition-Based Hyperspectral Resolution Enhancement for Mineral Mapping

Duan, Puhong ; Lai, Jibao ; Ghamisi, Pedram ; Kang, Xudong ; Jackisch, Robert ; Kang, Jian ; Gloaguen, Richard (2020-09-07)

Combining both spectral and spatial information with enhanced resolution provides not only elaborated qualitative information on surfacing mineralogy but also mineral interactions of abundance, mixture, and structure. This enhancement in the resolutions helps geomineralogic features such as small intrusions and mineralization become detectable. In this paper, we investigate the potential of the...

A Deep Multi-Attention Driven Approach for Multi-Label Remote Sensing Image Classification

Sumbul, Gencer ; Demir, Begüm (2020-05-19)

Deep learning (DL) based methods have been found popular in the framework of remote sensing (RS) image scene classification. Most of the existing DL based methods assume that training images are annotated by single-labels, however RS images typically contain multiple classes and thus can simultaneously be associated with multi-labels. Despite the success of existing methods in describing the in...

BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

Sumbul, Gencer ; Charfuelan, Marcela ; Demir, Begüm ; Markl, Volker (2019)

The BigEarthNet archive was constructed by the Remote Sensing Image Analysis (RSiM) Group and the Database Systems and Information Management (DIMA) Group at the Technische Universität Berlin (TU Berlin). This work is supported by the European Research Council under the ERC Starting Grant BigEarth and by the German Ministry for Education and Research as Berlin Big Data Center (BBDC). BigEarthN...

A Weighted SVM-Based Approach to Tree Species Classification at Individual Tree Crown Level Using LiDAR Data

Nguyen, Hoang Minh ; Demir, Begüm ; Dalponte, Michele (2019-12-09)

Tree species classification at individual tree crowns (ITCs) level, using remote-sensing data, requires the availability of a sufficient number of reliable reference samples (i.e., training samples) to be used in the learning phase of the classifier. The classification performance of the tree species is mainly affected by two main issues: (i) an imbalanced distribution of the tree species class...

Deep Metric and Hash-Code Learning for Content-Based Retrieval of Remote Sensing Images

Roy, Subhankar ; Sangineto, Enver ; Demir, Begüm ; Sebe, Nicu (2018-11-05)

The growing volume of Remote Sensing (RS) image archives demands for feature learning techniques and hashing functions which can: (1) accurately represent the semantics in the RS images; and (2) have quasi real-time performance during retrieval. This paper aims to address both challenges at the same time, by learning a semantic-based metric space for content based RS image retrieval while simul...

Advanced Local Binary Patterns for Remote Sensing Image Retrieval

Tekeste, Issayas ; Demir, Begüm (2018-11-05)

The standard Local Binary Pattern (LBP) is considered among the most computationally efficient remote sensing (RS) image descriptors in the framework of large-scale content based RS image retrieval (CBIR). However, it has limited discrimination capability for characterizing high dimensional RS images with complex semantic content. There are several LBP variants introduced in computer vision tha...

Retrieving Images with Generated Textual Descriptions

Hoxha, Genc ; Melgani, Farid ; Demir, Begüm (2019-11-14)

This paper presents a novel remote sensing (RS) image retrieval system that is defined based on generation and exploitation of textual descriptions that model the content of RS images. The proposed RS image retrieval system is composed of three main steps. The first one generates textual descriptions of the content of the RS images combining a convolutional neural network (CNN) and a recurrent ...

A Novel Multi-Attention Driven System for Multi-Label Remote Sensing Image Classification

Sumbul, Gencer ; Demir, Begüm (2019-11-14)

This paper presents a novel multi-attention driven system that jointly exploits Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in the context of multi-label remote sensing (RS) image classification. The proposed system consists of four main modules. The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial...

Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

Sumbul, Gencer ; Charfuelan, Marcela ; Demir, Begüm ; Markl, Volker (2019-11-14)

This paper presents the BigEarthNet that is a new large-scale multi-label Sentinel-2 benchmark archive. The BigEarthNet consists of 590, 326 Sentinel-2 image patches, each of which is a section of i) 120 × 120 pixels for 10m bands; ii) 60×60 pixels for 20m bands; and iii) 20×20 pixels for 60m bands. Unlike most of the existing archives, each image patch is annotated by multiple land-cover class...

A Novel Data Fusion Technique for Snow Cover Retrieval

De Gregorio, Ludovica ; Callegari, Mattia ; Marin, Carlo ; Zebisch, Marc ; Bruzzone, Lorenzo ; Demir, Begüm ; Strasser, Ulrich ; Marke, Thomas ; Günther, Daniel ; Nadalet, Rudi ; Notarnicola, Claudia (2019-06-27)

This paper presents a novel data fusion technique for improving the snow cover monitoring for a mesoscale Alpine region, in particular in those areas where two information sources disagree. The presented methodological innovation consists in the integration of remote-sensing data products and the numerical simulation results by means of a machine learning classifier (support vector machine), ca...

Approximating JPEG 2000 wavelet representation through deep neural networks for remote sensing image scene classification

Preethy Byju, Akshara ; Sumbul, Gencer ; Demir, Begüm ; Bruzzone, Lorenzo (2019-10-15)

This paper presents a novel approach based on the direct use of deep neural networks to approximate wavelet sub-bands for remote sensing (RS) image scene classification in the JPEG 2000 compressed domain. The proposed approach consists of two main steps. The first step aims to approximate the finer level wavelet sub-bands. To this end, we introduce a novel Deep Neural Network approach that util...