Showing papers in "IEEE Geoscience and Remote Sensing Magazine in 2019"
TL;DR: Current hyperspectral band selection methods are reviewed, which can be classified into six main categories: ranking based, searching based, clustering based, sparsity based, embedding-learning based, embedded learning based, and hybrid-scheme based.
Abstract: A hyperspectral imaging sensor collects detailed spectral responses from ground objects using hundreds of narrow bands; this technology is used in many real-world applications. Band selection aims to select a small subset of hyperspectral bands to remove spectral redundancy and reduce computational costs while preserving the significant spectral information of ground objects. In this article, we review current hyperspectral band selection methods, which can be classified into six main categories: ranking based, searching based, clustering based, sparsity based, embedding-learning based, and hybrid-scheme based. With two widely used hyperspectral data sets, we illustrate the classification performances of several popular band selection methods. The challenges and research directions of hyperspectral band selection are also discussed.
246 citations
TL;DR: An increase in remote sensing and ancillary data sets opens up the possibility of utilizing multimodal data sets in a joint manner to further improve the performance of the processing approaches with respect to applications at hand.
Abstract: The recent, sharp increase in the availability of data captured by different sensors, combined with their considerable heterogeneity, poses a serious challenge for the effective and efficient processing of remotely sensed data. Such an increase in remote sensing and ancillary data sets, however, opens up the possibility of utilizing multimodal data sets in a joint manner to further improve the performance of the processing approaches with respect to applications at hand. Multisource data fusion has, therefore, received enormous attention from researchers worldwide for a wide variety of applications. Moreover, thanks to the revisit capability of several
226 citations
TL;DR: To fully exploit the available multitemporal HS images and their rich information content in change detection (CD), it is necessary to develop advanced automatic techniques that can address the complexity of the extraction of change information in an HS space.
Abstract: The expected increasing availability of remote sensing satellite hyperspectral (HS) images provides an important and unique data source for Earth observation (EO). HS images are characterized by a detailed spectral sampling (i.e., very high spectral resolution) over a wide spectral wavelength range, which makes it possible to monitor land-cover dynamics at a fine spectral scale. This is due to its capability of detecting subtle spectral variations in multitemporal images associated with land-cover changes that are not detectable in traditional multispectral (MS) images because of their limited spectral resolution (i.e., sufficient for representing only abrupt, strong changes in the spectral signature, as a rule). To fully exploit the available multitemporal HS images and their rich information content in change detection (CD), it is necessary to develop advanced automatic techniques that can address the complexity of the extraction of change information in an HS space. This article provides a comprehensive overview of the CD problem in HS images, as well as a survey on the main CD techniques available for multitemporal HS images. We review both widely used methods and new techniques proposed in the recent literature. The basic concepts, categories, open issues, and challenges related to CD in HS images are discussed and analyzed in detail. Experimental results obtained using state-of-the-art approaches are shown, to illustrate relevant concepts and problems.
215 citations
TL;DR: The military- and security-driven applications of HSI are reviewed, which analyzes and demonstrates sensing capabilities and advanced methodologies, summarizes the current spaceborne and airborne military HSI technologies, and reviews future technological developments.
Abstract: Collecting airborne and spaceborne intelligence, surveillance, and reconnaissance (ISR) information is mandatory for addressing the defense challenges posed in the 21st century. A key tool for increasing the information content of ISR is using advanced electrooptical devices, including hyperspectral imaging (HSI). This optical sensing technology offers high spectral resolution covering visible to long-wave infrared (LWIR) wavelengths. The increase in spectral information and spectral degrees of freedom create a unique opportunity to detect difficult targets at the subpixel level, analyze a scene without prior information of the materials to be encountered, distinguish hidden features and camouflage, identify chemical agents in plumes, tag disturbed earth over buried objects, and perform image classification with greatly improved accuracy. This article reviews the military- and security-driven applications of HSI. It analyzes and demonstrates sensing capabilities and advanced methodologies, summarizes the current spaceborne and airborne military HSI technologies, and reviews future technological developments.
170 citations
TL;DR: This article describes innovative PU techniques and concepts related to multibaseline (MB) PU and large-scale (LS) PU in InSAR signal processing and discusses several numerical processing examples of these PU techniques.
Abstract: Synthetic aperture radar (SAR) interferometry (InSAR) is primarily used in remote-sensing applications and has created a new class of radar data that has significantly evolved during the last couple of decades. Most of the InSAR applications (e.g., topographic mapping and deformation monitoring) typically use a technique called phase unwrapping (PU). In this article, we present an overview of PU techniques in InSAR signal processing. First, we review the established single-baseline (SB) PU methods and then describe innovative PU techniques and concepts related to multibaseline (MB) PU and large-scale (LS) PU. In addition, we discuss several numerical processing examples of these PU techniques. It is our hope that this review will provide guidelines to future researchers to enhance further PU algorithmic developments.
166 citations
TL;DR: In this paper, the authors present the state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties that arise in the implementation of deep neural networks for this task.
Abstract: In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. This article presents the state of the art of previous machine-learning approaches, reviews the various deeplearning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties that arise in the implementation of deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided, and a software toolbox is publicly released to allow experimenting with these methods (https://github.com/nshaud/DeepHyperX). This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deeplearning techniques to their own data set.
114 citations
TL;DR: Image mosaicking is often a necessary process to cover a large and full region of interest (ROI) for many remote sensing applications (e.g., geographical mapping, resource and environmental monitoring, and disaster monitoring).
Abstract: Image mosaicking is often a necessary process to cover a large and full region of interest (ROI) for many remote sensing applications (e.g., geographical mapping, resource and environmental monitoring, and disaster monitoring).
82 citations
TL;DR: UAVs have many promising characteristics—flexibility, efficiency, high spatial/temporal resolution, low cost, easy operation, and so forth—that make them an effective complement to the other two platforms and a cost-effective means for remote sensing.
Abstract: The past few decades have witnessed great progress for unmanned aerial vehicles (UAVs) in civilian fields, especially in photogrammetry and remote sensing. In contrast with manned aircraft and satellites, UAVs have many promising characteristicsmflexibility, efficiency, high spatial/temporal resolution, low cost, easy operation, and so forthmthat make them an effective complement to the other two platforms and a cost-effective means for remote sensing.
75 citations
Chinese Academy of Sciences1, Shandong Normal University2, Zhejiang University3, East China University of Science and Technology4, Harbin Institute of Technology5, Tongji University6, Jiangnan University7, Shanghai Maritime University8, Nanjing University of Aeronautics and Astronautics9, Anhui University10, Ningbo University11
TL;DR: The Advanced Hyperspectral Imager (AHSI) as discussed by the authors is the first spaceborne hyperspectral sensor that utilizes both a convex-grating spectrophotometry and an improved three-concentric-mirror (Offner) configuration.
Abstract: This article introduces the design and imaging principles of the Advanced Hyperspectral Imager (AHSI) aboard China's GaoFen-5 satellite. The AHSI is a visible and nearinfrared (VNIR)/short-wave infrared (SWIR) HSI. It is the first spaceborne hyperspectral sensor that utilizes both a convex-grating spectrophotometry and an improved three-concentric-mirror (Offner) configuration. It has 330 spectral bands, a 60-km swath width, and a 30-m spatial resolution. Various tests have been designed to evaluate its imaging performance, and the results indicate that the AHSI's performance is comparable to other spaceborne HSIs launched recently and those scheduled for launch in the next few years. The AHSI has the capability to detect and identify different ground objects.
70 citations
TL;DR: This article constructs a general processing scheme for UIS detection, provides four categories of major methods, and proposes a deep compressive-based convolutional deep belief network (dc-CDBN) method and a novel classification strategy for multisource data fusion models.
Abstract: Urban impervious surface (UIS) offers potentially valuable information for the development of sustainable urban management strategies and environmental change monitoring actions. In this article, we focus on UIS-detection-related issues, identify and analyze systematic challenges, construct a general processing scheme for UIS detection, provide four categories of major methods, and propose a deep compressive-based convolutional deep belief network (dc-CDBN) method and a novel classification strategy for multisource data fusion models.
42 citations
TL;DR: In this article, the spectral response for a given material exhibits considerable variability from a variety of causes: intrinsic, depending on the composition or morphology of the material, extrinsic (depending on the size of an object or the concentration of the materials), or environmental (due to illumination, atmospheric distortion, and so on).
Abstract: The central problem in hyperspectral remote sensing is characterizing the material components of a scene based on the spectral radiance observed in the image pixels. What makes this challenging is the fact that the spectral response for a given material exhibits considerable variability from a variety of causes: intrinsic (depending on the composition or morphology of the material), extrinsic (depending on the size of an object or the concentration of the material), or environmental (due to illumination, atmospheric distortion, and so on). In this article, we survey many of the causes of spectral variability, describe spectral models for this variability, and outline some signal processing and target detection strategies for analyzing hyperspectral data in a way that is more robust to this variability.
TL;DR: In this paper, the authors discuss the unique aspects of thermal infrared hyperspectral imaging, review the progress that has been made, and highlight existing challenges and areas for future research.
Abstract: Longwave infrared (LWIR) hyperspectral imaging (HSI) sensors provide valuable information for numerous military, scientific, and commercial applications. The hyperspectral signal exploitation principles are the same in the reflective and emissive regions of the spectrum. However, the underlying phenomenology and interaction with the environment are different in the two regimes of the spectrum. These differences affect all aspects of thermal IR HSI, from sensor design to data exploitation. The main objective of this article is to explain the unique aspects of thermal IR HSI, review the progress that has been made, and highlight existing challenges and areas for future research.
TL;DR: Through a series of scientific challenges, participants must solve remote sensing problems using multimodal data, leveraging new sensors and big data, and applying emerging methods to extract geospatial information.
Abstract: F or more than a decade, the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (GRSS) has been organizing the Data Fusion Contest (DFC). Through a series of scientific challenges, participants must solve remote sensing problems using multimodal data, leveraging new sensors and big data, and applying emerging methods to extract geospatial information [1]–[13].
TL;DR: In this paper, the authors examined atmospheric compensation of hyperspectral data in the visible and near-infrared (VNIR)-short-wave infrared (SWIR) region.
Abstract: In this tutorial overview, we examine atmospheric compensation of hyperspectral data in the visible and nearinfrared (VNIR)-short-wave infrared (SWIR) region. The background is discussed, including the motivation for and a brief history of image compensation. Atmospheric characteristics are presented to highlight important optical effects that must be mitigated (i.e., atmospheric absorption and scattering). A full radiative transfer (RT) expression with simplifications is presented, resulting in formulations that are solved in terms of reflectance.
TL;DR: In this paper, a geophysical mine-prospecting technology for predicting geological hazards has attracted increasing attention in coal mines in China, where 20 serious flooding accidents occurred in Chinese coal mines that caused heavy casualties and property losses.
Abstract: Around 1985, there were 20 serious flooding accidents in Chinese coal mines that caused heavy casualties and property losses. As a result, geophysical mine-prospecting technologies for predicting geological hazards have attracted increasing attention.
TL;DR: In this paper, a forward model is proposed for calculating the FDEM instrument response theoretically, e.g., during an inversion, and can be used for additional purposes, such as instrument calibration, synthetic data generation, depth of investigation estimation, instrument design, survey design, assessment of the detection limit for a given target within a known host body, and educational purposes.
Abstract: Frequency-domain electromagnetic (FDEM) data are commonly acquired to provide spatially continuous information about subsurface electrical conductivity (EC) and/or magnetic susceptibility [1]. To link the phase-sensitive instrument responses?the quadrature-phase (QP) and in-phase (IP) components of the EM field (i.e., data space)-with the subsurface physical properties (i.e., model space), a forward model is indispensable. In addition, a forward model is essential for calculating the FDEM instrument response theoretically, e.g., during an inversion, and can be used for additional purposes, such as instrument calibration, synthetic data generation, depth of investigation estimation, instrument design, survey design, assessment of the detection limit for a given target within a known host body, apparent EC estimation, and educational purposes [2]-[7].
TL;DR: In this article, the authors used the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), a satellite-borne instrument, to map mineral groups in the short-wave infrared (SWIR) and thermal infrared (IR) bands.
Abstract: Geologists have been instrumental in shaping Earth observation satellite missions; likewise, geology has been the subject of many remote sensing studies [1]. Applications of optical remote sensing in geology date back to some early studies using the Earth Resources Technology Satellite-1 , the predecessor of the Landsat satellite program [2]. In the 1980s, the seventh channel in the short-wave infrared (SWIR) of the Landsat thematic mapper program was added, as a result of spectroscopic mineral studies by geologists [58]. A subsequent satellite-borne instrument, the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), launched in 1999, had specific bands in the SWIR and thermal infrared dedicated to mapping mineral groups [3].
TL;DR: The use of UAVs has generated a great deal of controversy, partly because of their use for military and police purposes and because of concerns that they pose threats to privacy and safety as mentioned in this paper.
Abstract: Unmanned aerial vehicles (UAVs), commonly called drones, have generated a great deal of controversy, partly because of their use for military and police purposes and because of concerns that they pose threats to privacy and safety. At the same time, environmental scientists are finding drones to be a powerful research tool. Because the use of drones has the potential to generate sensitive and incidental information (especially about human activities), environmental scientists must think carefully about how to handle these findings in ethically appropriate ways that do not generate a backlash against their use.
TL;DR: In this article, the authors analyzed venture capital investments in the Earth observation (EO) industry, with the aim of identifying technology trends, and collected tech-and investment-related publicly available data on all private, nonsubsidiary companies using their own satellite constellation or other EO instruments as needed to solve the problem of remote sensing of Earth's surface in the optical part of the electromagnetic spectrum and that were attracting investment and announcing plans for the future.
Abstract: This article analyzes venture capital (VC) investments in the Earth observation (EO) industry, with the aim of identifying technology trends. We collected tech- and investment-related publicly available data on all private, nonsubsidiary companies using their own satellite constellation or other EO instruments as needed to solve the problem of remote sensing of Earth's surface in the optical part of the electromagnetic spectrum and that were attracting investment and announcing plans for the future, as of 31 December 2016. We refer to these companies as EO startups. In the final sample, there are nine EO start-ups and 21 instruments used in their missions.
TL;DR: Using the most widely used PM2.5 concentration remote sensing product, provided by Dalhousie University, Halifax, Canada, Wang et al. as discussed by the authors investigated the use and misuse of remotely sensed PM 2.5 data sets in China.
Abstract: Remote sensing has been widely and increasingly used to quantify fine-particulate matter (PM2.5) concentrations globally; however, its uncertainty has not been well tested in countries, such as China and India, where serious PM2.5 pollution occurs, which may lead to misuse of the data. Utilizing the most widely used PM2.5 concentration remote sensing product, provided by Dalhousie University, Halifax, Canada, we investigated the use and misuse of remotely sensed PM2.5 concentration data sets in China.
TL;DR: The Global Learning and Observations to Benefit the Environment (GLOBE) program is an international science and education initiative that gives students and the public worldwide an opportunity to participate in data collection and the scientific process and to contribute meaningfully to our understanding of Earth and the global environment as discussed by the authors.
Abstract: The Global Learning and Observations to Benefit the Environment (GLOBE) program is an international science and education initiative that gives students and the public worldwide an opportunity to participate in data collection and the scientific process and to contribute meaningfully to our understanding of Earth and the global environment. GLOBE launched in 1995, with the vision of bringing a worldwide community of students, teachers, scientists, and citizens together to better understand, sustain, and improve Earth's environment at local, regional, and global scales (https://www.globe.gov/about/overview).
TL;DR: The D3MOBILE Metrology World League as mentioned in this paper was established in 2013 with the goal of encouraging curiosity about and interest in science (particularly geoscience) with secondary students of the International Standard Classification of Education (ISCED) grades 1 and 2.
Abstract: The D3MOBILE Metrology World League was established in 2013 with the goal of encouraging curiosity about and interest in science (particularly geoscience) with secondary students of the International Standard Classification of Education (ISCED) grades 1 and 2. Presented as an international championship, D3MOBILE introduces students to the discipline of photogrammetry through the e-learning methodology concept. Pupils' use of wellknown technologies, such as their own mobile devices (smartphones or tablets), allows educators to develop attractive and challenging teaching procedures. All work proposed for participants is presented using scientific, technical, and professional language but in a more interactive format than with traditional textbooks or theoretical classes. The challenges, which provide students with the opportunity to establish their own learning objectives, encourage both teamwork and individual responsibility.
TL;DR: Remote sensing images have been broadly employed over the past decades to detect and investigate temporal changes on Earth's surface to support complex analyses of temporal data in various domains, ranging from purely scientific to educational.
Abstract: Remote sensing images have been broadly employed over the past decades to detect and investigate temporal changes on Earth's surface. Appropriate tools are needed to support complex analyses of temporal data in various domains, ranging from purely scientific to educational. There are many existing tools, but it is often necessary to switch among them several times. Typical interoperability issues include system mismatch and the variety of user profiles and data types.
TL;DR: An analysis of 32 student projects showed that the educational program fostered a variety of important science competencies, and the students thought the program was interesting and meaningful.
Abstract: As a versatile and multidisciplinary area of scientific research with diverse applications for everyday life, satellite remote sensing presents a particularly suitable context for science education. In this article, we give a short overview of how self-acquired infrared remote sensing data can be applied in individual remote sensing projects conducted by high school students in their own environments. We conducted a joint pilot project with students from Beer-Sheva, Israel, and Munich, Germany. The students were tasked with acquiring and analyzing remote sensing measurements in the field. The educational program was evaluated through a questionnaire and by observing the students. Our analysis of 32 student projects showed that the educational program fostered a variety of important science competencies, and the students thought the program was interesting and meaningful.
TL;DR: For a comprehensive look at the characteristics, phenomenology, algorithms, and applications of hyperspectral images, see as discussed by the authors. But, the focus of this special issue is on the characteristics and applications.
Abstract: Hyperspectral imaging (HSI) for geoscience remote sensing and Earth observation has been around since the mid-1980s. For many years, it was the purview of research laboratories and proof-of-concept satellite missions. Hundreds of research articles have been published exploring algorithms for analysis and demonstrating applications across many Earth observational fields of interest. Most have focused on a relatively small group of publicly available data sets due to the high cost of sensor operation and collection of ground reference data necessary for algorithm and product evaluation. More recently, as the cost of focal planes and sensor technology has decreased, together with the emergence of inexpensive unmanned aerial vehicle (UAV) systems and Cube- Sats/smallSats in space access, the availability of hyperspectral imagery is poised to grow dramatically. Several airborne and spaceborne systems have been deployed or are being planned. Commercial remote sensing and image processing software systems provide more support and extended functionality for such data, while the practical use of hyperspectral data in both commercial and scientific applications has increased. The community now has access to relatively low-cost UAV systems and data and will soon see more routine availability of space-based HSI data. This special issue of IEEE Geoscience and Remote Sensing Magazine on HSI was put together based on the recognition that the field is on the cusp of expanded data availability. While formerly the domain of a relatively small group of specialists, it is anticipated HSI data will soon become available to a wider range of scientists and data users. This special issue was compiled to bring together a comprehensive look at the characteristics, phenomenology, algorithms, and applications as a resource for practitioners and students who wish to gain familiarity with the field.
TL;DR: The main goal of the Algerian GRS community is maintaining a motivated and professional GRSS Chapter by connecting researchers, academics, students, industry representatives, and members working in GRS and related areas as mentioned in this paper.
Abstract: JUNE 2019 IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE to set up common national projects with socioeconomic impacts ◗ establishing collaborations with other GRSS Chapters, especially those in Europe and the Middle East and North Africa regions ◗ extending the Executive Committee to include regional and student Chapter coordinators ◗ encouraging young researchers to become GRSS members ◗ creating an international GRS online master’s program. The Algerian GRS community is very fruitful and will offer many opportunities in these fields over the coming years. The main goal of this community is maintaining a motivated and professional GRSS Chapter by connecting researchers, academics, students, industry representatives, and members working in GRS and related areas. We can succeed in this challenge with the help and support of the GRSS.
TL;DR: This issue of IEEE Geoscience and Remote Sensing Magazine (GRSM), the roles of IEEE Women in Engineering (WIE) in terms of these important GRSS training and scientific conferences are highlighted.
Abstract: In this "Women in GRSS" column, we highlight the roles of women in organizing some IEEE Geoscience and Remote Sensing Society (GRSS) summer training programs this year as well as the upcoming 2020 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) that is in preparation for next year. Organizing a summer training program or an international scientific conference is a major undertaking, but it can also be a professionally enriching and personally rewarding activity. For this issue of IEEE Geoscience and Remote Sensing Magazine (GRSM), we highlight the roles of IEEE Women in Engineering (WIE) in terms of these important GRSS training and scientific conferences.