Commercial Imagery Research Articles

Super-resolution deep neural networks for water classification from free multispectral satellite imagery

Recent years have seen rapid progress in the adoption of fully convolutional neural networks (FCN) to classify optical satellite imagery, made possible by a combination of new FCN architectures, next-generation GPUs, and publicly available satellite imagery from, e.g., the Landsat and Sentinel missions. These satellites offer repeat global coverage at intervals of only a few days at a spatial resolution of ≥10 m, which is sufficient for some but not all applications of interest. A smaller body of literature considers similar tools to classify commercial satellite imagery that offer 1 – 2 orders of magnitude higher spatial resolutions but with limited spatial and temporal coverage. In this work, we develop a super-resolution FCN to achieve the best of both worlds: land cover classification at commercial-level spatial resolutions but with the spatiotemporal coverage of public satellite imagery. To do so, we label 1 – 2 m resolution commercial imagery and use this as training data for super-resolution FCN. As a specific application, we focus on the segmentation of rivers, with the goal of tracking changes in reach-averaged river widths, depths, and discharges over time. We present detailed performance analyses and demonstrate that, surprisingly, we achieve ≳ 90% classification accuracy at meter-scale resolutions from free Sentinel-2 imagery. We extensively validate our model through in situ USGS gage data and ground-truth GPS tracing of river shorelines. By making our super-resolution FCN codes and training weights publicly available, we hope that these tools will be of use to the broader hydrology community and beyond, as the models can be re-trained for other segmentation tasks.

User-Relevant Land Cover Products for Informed Decision-Making in the Complex Terrain of the Peruvian Andes

Land cover in mountainous regions is shaped by a complex web of stressors arising from natural and anthropogenic processes. The co-design process implemented with regional stakeholders in this study highlighted persistent data gaps and the need for locally relevant (thematic, spatial, and temporal) data products, which global alternatives still fail to deliver. This study describes the development of a land cover database designed for the Junín National Reserve (JNR) in Peru as a precursor of a broader effort designed to serve Andean wetland ecosystems. The products were created using Random Forest models leveraging Sentinel-1 and Sentinel-2 data and trained using a large database of in situ data enhanced by the use of high-resolution commercial imagery (Planet). The land cover basemap includes eight classes (two of vegetation) with an overall accuracy of 0.9 and Cohen’s Kappa of 0.93. A second product further subdivided vegetation into locally meaningful vegetation classes, for a total of four types (overall accuracy of 0.85). Finally, a surface water product (snapshot and frequency) delivered a representation of the highly variable water extent around Lake Junín. It was the result of a model incorporating 150 Sentinel-1 images from 2016 to 2021 (an overall accuracy of 0.91). The products were successfully employed in identifying 133 ecosystem services provided by the different land cover classes existing in the JNR. The study highlights the value of participatory monitoring and open-data sharing for enhanced stewardship of social-ecological systems.

Mapping retrogressive thaw slumps using deep neural networks

Retrogressive thaw slumps (RTS) are thermokarst features in ice-rich hillslope permafrost terrain, and their occurrence in the warming Arctic is increasingly frequent and has caused dynamic changes to the landscape. RTS can significantly impact permafrost stability and generate substantial carbon emissions. Understanding the spatial and temporal distribution of RTS is a critical step to understanding and modelling greenhouse gas emissions from permafrost thaw. Mapping RTS using conventional Earth observation approaches is challenging due to the highly dynamic nature and often small scale of RTS in the Arctic. In this study, we trained deep neural network models to map RTS across several landscapes in Siberia and Canada. Convolutional neural networks were trained with 965 RTS features, where 509 were from the Yamal and Gydan peninsulas in Siberia, and 456 from six other pan-Arctic regions including Canada and Northeastern Siberia. We further tested the impact of negative data on the model performance. We used 4-m Maxar commercial imagery as the base map, 10-m NDVI derived from Sentinel-2 and 2-m elevation data from the ArcticDEM as model inputs and applied image augmentation techniques to enhance training. The best-performing model reached a validation Intersection over Union (IoU) score of 0.74 and a test IoU score of 0.71. Compared to past efforts to map RTS features, this represents one of the best-performing models and generalises well for mapping RTS in different permafrost regions, representing a critical step towards pan-Arctic deployment. The predicted RTS matched very well with the ground truth labels visually. We also tested how model performance varied across different regional contexts. The result shows an overall positive impact on the model performance when data from different regions were incorporated into the training. We propose this method as an effective, accurate and computationally undemanding approach for RTS mapping.

JOINT SUPER-RESOLUTION AND IMAGE RESTORATION FOR PLÉIADES NEO IMAGERY

Abstract. Modern Earth Observation optical satellite systems, such as Airbus’s Pleiades Neo (PNeo) push the boundaries of high spatial resolution by providing commercial imagery products with up to 30cm ground sampling distance (GSD). To further enhance the quality of the images, the in-space imaging system is usually complemented by on-ground image restoration processing, such as deconvolution and denoising (Latry et al., 2012). Recent advances leverage Convolutional Neural Networks (CNNs) to improve the image restoration quality (K. Zhang et al., 2021a).Single Image Super-Resolution (SISR), or Zoom, the process of obtaining a higher resolution (HR) image from a lower resolved (LR) source, has recently gained traction for both medium resolution sensors such as Sentinel 2 (Lanaras et al., 2018) and high resolution such as Pléiades and GeoEye-1 (Zhu et al., 2020). This process further enhances the resolution of the image to improve downstream applications such as mapping (L. Zhang et al., 2021) and small objects recognition (Shermeyer and Van Etten, 2019). While SISR for remote sensing has been successfully tackled using CNNs (Rohith and Kumar, 2021) the main challenge for reaching acceptable image quality performance lies in the generation of realistic LR/HR training pairs (K. Zhang et al., 2021b). In this paper, we propose:a dedicated simulation chain leveraging extremely-high-resolution (EHR) aerial imagery to generate realistic 30cm Pléiades Neo images and their corresponding fully restored HR equivalent at 15cm GSDA residual-based CNN architecture which we train to jointly restore and zoom the images All contributions are assessed on real PNEO images.We deployed the trained models in a production context, to enhance the full Pléiades Neo products – with a swath of 47k pixels – in an efficient and scalable manner.

Beyond “Commercial Realism”: Extending Goffman’s Gender Display Framework to Networked Media Contexts

Abstract Erving Goffman’s gender display framework is a typology of nonverbal posing codes that connote the subordination of women in commercial imagery and a prominent tool for assessing visualizations of gender stereotyping in mass media. Researchers have recently begun to apply the advertisement-based framework to a new context: user-generated social media photos. Despite findings that gender display appears prevalent in such images, deeper critical examinations of how the framework changes when applied across media contexts have not been meaningfully undertaken. Drawing from the interplay of Goffman’s concepts of hyper-ritualization and commercial realism, I argue that the manifestations and interpretive implications of gender display are contingent upon the standard of realism at play, proposing a standard of networked realism that differently modulates gender display in user-generated photography. Ultimately, I suggest that gender display must be more thoroughly contextualized in networked media research and provide a groundwork for future feminist studies of visual gender stereotyping.

Understanding the synergies of deep learning and data fusion of multispectral and panchromatic high resolution commercial satellite imagery for automated ice-wedge polygon detection

The utility of sheer volumes of very high spatial resolution (VHSR) commercial imagery in mapping the Arctic region is new and actively evolving. Commercial satellite sensors typically record image data in low-resolution multispectral (MS) and high-resolution panchromatic (PAN) mode. Spatial resolution is needed to accurately describe feature shapes and textural patterns, such as ice-wedge polygons (IWPs) that are rapidly transforming surface features due to degrading permafrost, while spectral resolution allows capturing of land-use and land-cover types. Data fusion, the process of combining PAN and MS images with complementary characteristics often serves as an integral component of remote sensing mapping workflows. The fusion process generates spectral and spatial artifacts that may affect the classification accuracies of subsequent automated image analysis algorithms, such as deep learning (DL) convolutional neural nets (CNN). We employed a detailed multidimensional assessment to understand the performances of an array of eight application-oriented data fusion algorithms when applied to VHSR image scenes for DLCNN-based mapping of ice-wedge polygons. Our findings revealed the scene dependency of data fusion algorithms and emphasized the need for careful selection of the proper algorithm. Results suggested that the fusion algorithms that preserve spatial character of original PAN imagery favor the DLCNN model performances. The choice of fusion approach needs to be considered of equal importance to the required training dataset for successful applications using DLCNN on VHRS imagery in order to enable an accurate mapping effort of permafrost thaw across the Arctic region.

Image Collection Simulation Using High-Resolution Atmospheric Modeling

A new method is described for simulating the passive remote sensing image collection of ground targets that includes effects from atmospheric physics and dynamics at fine spatial and temporal scales. The innovation in this research is the process of combining a high-resolution weather model with image collection simulation to attempt to account for heterogeneous and high-resolution atmospheric effects on image products. The atmosphere was modeled on a 3D voxel grid by a Large-Eddy Simulation (LES) driven by forcing data constrained by local ground-based and air-based observations. The spatial scale of the atmospheric model (10–100 m) came closer than conventional weather forecast scales (10–100 km) to approaching the scale of typical commercial multispectral imagery (2 m). This approach was demonstrated through a ground truth experiment conducted at the Department of Energy Atmospheric Radiation Measurement Southern Great Plains site. In this experiment, calibrated targets (colored spectral tarps) were placed on the ground, and the scene was imaged with WorldView-3 multispectral imagery at a resolution enabling the tarps to be visible in at least 9–12 image pixels. The image collection was simulated with Digital Imaging and Remote Sensing Image Generation (DIRSIG) software, using the 3D atmosphere from the LES model to generate a high-resolution cloud mask. The high-resolution atmospheric model-predicted cloud coverage was usually within 23% of the measured cloud cover. The simulated image products were comparable to the WorldView-3 satellite imagery in terms of the variations of cloud distributions and spectral properties of the ground targets in clear-sky regions, suggesting the potential utility of the proposed modeling framework in improving simulation capabilities, as well as testing and improving the operation of image collection processes.

Tarrying with the elephant: Queer villainy and aesthetic pleasure in Steven Klein’s photography

Through a close reference to Steven Klein’s photo spread ‘John Robinson’ for L’Uomo Vogue in 2003, this article tracks the appearance of the fictional character of the queer villain in fashion editorial photography. It discusses specifically how the register of ‘affectlessness’ is embodied and aesthetically performed by the queer villain. Affectlessness is contextualized within the repertoire of neutral affects that were circulated in fashion photography in the late 1990s and early 2000s as an aesthetic stance that counteracted the normative depictions of ‘happy feelings’ in commercial imagery as well as normative styles of masculinity. Affective states of sadness, alienation and neutrality were enacted beginning in the 1990s primarily by androgynous and sexually ambivalent figures: the stylized representation of such states signalled a challenge to binary ways of embodying and performing masculinity and femininity. After a critical reading of ‘John Robinson’, the article concludes by tracing a speculative trajectory for thinking about aesthetic pleasure in relation to queer amoral characters in fashion visual narratives.

From corruption to perversion: sexually explicit imagery, forensic medicine, and sexual psychopathology (1862–1927)

ABSTRACT Inventories of commercial imagery considered obscene or pornographic were first seen in the latter half of the 1900s, in the form of grass-roots initiatives by European public morality protectors Ludwig Kemmer, Louis Comte, and Comte’s disciple Émile Pourésy. Research became a coordinated exercise in Germany in the 1920s, led by Berlin detective superintendent Detloff von Behr. These hostile inventories speak to the practical historical interrelation between demarcations of the obscene and the perverse. Despite perennial allusions to its corrupting nature, neither producers nor consumers of explicit photography acquired a robust profile in early twentieth-century sexual psychopathology and sexology more generally. Beyond the perennial appropriation of medical epithets by moral hygienists, pornography was long denied the status of a forensic psychological problem. It was the early trailblazers of the anti-obscenity movement who mobilized the nineteenth-century diagnostic parlance of sexual derailment (sadism, satyrism, perversion, erotomania); in response, polemicists diagnosed prudes as cases of erotophobia and pornolagny. The German contributors highlighted the existence of a diversified ‘perverted’ content and Von Behr showed the greatest aspiration to thus extend the subject’s salience for forensic psychiatry, although he ultimately earned little recognition in ensuing discussions, whether of public decency or sexual psychology.

Why Standards Matter – The objectives and roadmap of the International Open Geospatial Consortium (OGC)

The vision and mission of the Open Geospatial Consortium is discussed, with emphasis on its role to bring the power of location to decision makers around the world. OGC standards have significantly improved location information sharing worldwide and enable rapid integration of location data and technologies used in traditional mapping. OGC’s focus now is to improve decision making through the efficient application of location to a range of social, economic and environmental topics. OGC standards facilitate the rapid mobilization of new data sources (e.g. commercial imagery, LIDAR) and new and disruptive technologies (e.g. IoT, autonomous and unmanned systems) to address challenges related to climate change, water resource availability, urban planning and management, insurance risk assessment, public safety, alternative energy placement, and land administration to name a few.

A fragile transparency: satellite imagery analysis, non-state actors, and visual representations of security

A broad range of non-state actors make use of commercial satellite imagery to monitor global security issues. Questioning the favourable narrative of achieving ‘global transparency’ through Earth observation, the article unravels the underlying relations between the US government, commercial imagery providers, and other non-state actors. Linking insights from Science and Technology Studies and International Relations, two related arguments are put forward: first, the commercialization of satellite technology and imagery does not dismiss the influence of the state but is conducive of the co-production of shifting actor constellations and related to that, different ideas about transparency and power. Secondly, this leads to a less benign understanding of transparency which emphasizes its contingent emergence, limited scope, and context dependence. This ‘fragile transparency’ exposes the shifting power relations inherent to commercial satellite imagery and its potential as a political practice to render certain things as visible and threats to international security.

Recent field experiments with commercial satellite imagery direct downlink

US Pacific Command's strategy includes assistance to United States government relief agencies and nongovernment organizations during humanitarian aid and disaster relief operations in the Asia-Pacific region. Situational awareness during these operations is enhanced by broad interagency access to unclassified commercial satellite imagery. The Remote Ground Terminal-a mobile satellite downlink ground station-has undergone several technology demonstrations and participated in an overseas deployment exercise focused on a natural disaster scenario. This ground station has received new commercial imagery within 20 minutes, hastening a normally days-long process. The Army Geospatial Center continues to manage technology development and product improvement for the Remote Ground Terminal. Furthermore, this ground station is now on a technology transition path into the Distributed Common Ground System-Army program of record.

When corporations come to define the visual politics of gender

Abstract While stock photographs have come to saturate media and have been mocked for their clichéd nature, for example where women are pictured laughing alone with salad, a powerful corporation like Getty Images that disseminates commercial imagery globally has sought to challenge these stereotypes by making more politicized images. This article examines one such case, that is, Getty’s Genderblend visual trend, which claims to portray gender identities and relations in ways that are both more inclusive and diverse, harnessing feminist theory as part of its promotion. Taking a multimodal discourse and visual design approach, the article looks at how corporate imagery can be styled as political and, in turn, how a politics of difference itself is shaped in the interests of the ideologies of consumer capitalism.

An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

The logistical challenges of Antarctic field work and the increasing availability of very high resolution commercial imagery have driven an interest in more efficient search and classification of remotely sensed imagery. This exploratory study employed geographic object-based analysis (GEOBIA) methods to classify guano stains, indicative of chinstrap and Adélie penguin breeding areas, from very high spatial resolution (VHSR) satellite imagery and closely examined the transferability of knowledge-based GEOBIA rules across different study sites focusing on the same semantic class. We systematically gauged the segmentation quality, classification accuracy, and the reproducibility of fuzzy rules. A master ruleset was developed based on one study site and it was re-tasked “without adaptation” and “with adaptation” on candidate image scenes comprising guano stains. Our results suggest that object-based methods incorporating the spectral, textural, spatial, and contextual characteristics of guano are capable of successfully detecting guano stains. Reapplication of the master ruleset on candidate scenes without modifications produced inferior classification results, while adapted rules produced comparable or superior results compared to the reference image. This work provides a road map to an operational “image-to-assessment pipeline” that will enable Antarctic wildlife researchers to seamlessly integrate VHSR imagery into on-demand penguin population census.

An automated, open-source pipeline for mass production of digital elevation models (DEMs) from very-high-resolution commercial stereo satellite imagery

We adapted the automated, open source NASA Ames Stereo Pipeline (ASP) to generate digital elevation models (DEMs) and orthoimages from very-high-resolution (VHR) commercial imagery of the Earth. These modifications include support for rigorous and rational polynomial coefficient (RPC) sensor models, sensor geometry correction, bundle adjustment, point cloud co-registration, and significant improvements to the ASP code base. We outline a processing workflow for ∼0.5m ground sample distance (GSD) DigitalGlobe WorldView-1 and WorldView-2 along-track stereo image data, with an overview of ASP capabilities, an evaluation of ASP correlator options, benchmark test results, and two case studies of DEM accuracy. Output DEM products are posted at ∼2m with direct geolocation accuracy of <5.0m CE90/LE90. An automated iterative closest-point (ICP) co-registration tool reduces absolute vertical and horizontal error to <0.5m where appropriate ground-control data are available, with observed standard deviation of ∼0.1–0.5m for overlapping, co-registered DEMs (n=14,17). While ASP can be used to process individual stereo pairs on a local workstation, the methods presented here were developed for large-scale batch processing in a high-performance computing environment. We are leveraging these resources to produce dense time series and regional mosaics for the Earth’s polar regions.

The long march of pop: art, music, and design, 1930-1995

Thomas Crow's paradigm-changing book challenges existing narratives about the rise of Pop Art by situating it within larger cultural tides. While American Pop was indebted to its British predecessor's insistence that any creative pursuit is worthy of aesthetic consideration, Crow demonstrates that this inclusive attitude also had strong American roots. Folk becomes Crow's starting point in the advance of Pop. The folk revival occurred chiefly in the sphere of music during the 1930s and '40s, while folk art surfaced a decade later in the work of Jasper Johns and Robert Rauschenberg. Crow eloquently examines the subsequent explosion of commercial imagery in visual art, alongside its repercussions in popular music and graphic design. Pop's practitioners become defined as artists whose distillation of the vernacular is able to capture the feelings stirring among a broad public, beginning with young participants in the politicized 1960s counterculture. Woody Guthrie and Roy Lichtenstein, Andy Warhol and Bob Dylan, Ed Ruscha and the Byrds, Pauline Boty and the Beatles, the Who and Damien Hirst are all considered together with key graphic designers such as Milton Glaser and Rick Griffin in this engaging book.

Calibration of digital camera integration accuracy for low-cost oblique aerial photogrammetry

This work describes a calibration process for inexpensive consumer cameras integrated into a low cost and compact aerial multi-view imager for remote sensing and photogrammetry. The main advantage of this design is to make the filming component lightweight and rapidly deployable, as well as reducing cost when compared with mainstream commercial oblique imagery. An in situ flight test was carried out in Guiyang. In that experiment, a meridian convergence-based approach was adopted to adjust preprocessing, the residue error and the captured images’ exterior orientation linear and angular parameters were calculated by means of the direct geo-referencing approach yielding a favorable outcome for exterior orientation linear parameters of the camera, around 0.2–0.3 m deviation from the actual measured results at 1000 m flight above ground level. The camera’s exterior orientation angular parameters φ, ω whose difference compared with the standard aerial aero triangulation approach reached a high accuracy level within the intended endurance of 0.005°. These results indicate that the compact implementation of the oblique aerial imager comprised of consumer level off-the-shelf digital cameras achieved competitive accuracy at a low cost and high versatility.

High-resolution landcover classification using Random Forest

Potential data sets for landcover classification, such as Landsat (or pre-processed data such as the National Land Cover Dataset (NLCD)), are often too coarse for fine-scale research needs or are cost-prohibitive (Quickbird, Ikonos and Geoeye). Repeated attempts at classifying high spatial resolution data, National Agricultural Imagery Program (NAIP) imagery, based on traditional techniques, such as a maximum likelihood supervised classification, have failed to produce a product with sufficient accuracy. We used the ensemble Random Forests (RFs) classifier to classify landcover at 1 m resolution using 2009 NAIP imagery in south-eastern Wyoming. We classified riparian areas within a 225 km2 study area, at 1 m spatial resolution, using RFs with emphasis on riparian corridors that yielded a land cover map with overall accuracy of 81% and a kappa coefficient of 79%. Users’ accuracy of important riparian vegetation species, aspen, riparian grasses and willow were 79%, 81% and 83%, respectively. Techniques presented in this paper, which exploit free NAIP imagery for landcover classification, represent an inexpensive and reliable alternative to purchasing commercial imagery when high spatial resolution landcover data is needed.

Editorial Introduction

Editorial Introduction Linda M. Scott Have we exhausted our modes of representation in advertising, and are we now suffering from marketing fatigue? Our first issue for 2014 considers old and new advertising technologies, focusing primarily on their relationship with the human being as a body and as an identity. As the authors of this issue set out, humanness has figured ubiquitously in the history of advertising as a vehicle of representation, as a heuristic, and as a site of consumption. Tracing a long and rich history of human billboarding, Susan McFarlane-Alvarez brings to attention recent advertising efforts that involve the human body as a site for promotion, or as a living component thereof. Resisting the temptation of apocalyptic judgment, McFarlane-Alvarez suggests these phenomena are expressive of new notions of human agencies and free-willed choices, strategically leveraged to achieve relevancy in an increasingly saturated media landscape. Although it is unlikely that selling our foreheads as advertising space to the highest bidder will become a trivial occurrence, “Human Billboarding: Peopled Publicity and a New Space of “Agency” in Advertising” intimates the many potentialities of the body’s involvement in the advertising landscape. Returning to somewhat more traditional forms of advertising, Joshua Shaffer elaborates on this thought in “Innovating Advertising: Conventional vs. Innovative Anthropomorphic Advertising Approaches in the 21st Century.” Awarded the Alfred J. Seaman Award for Best Undergraduate Paper on Advertising and Society at the AEF’s Honors Night 2013, Shaffer provides an overview of new anthropomorphic tendencies in contemporary ads and draws distinctions between “conventional” and “innovative” anthropomorphisms. Whereas Geico's gecko is exemplary of the former, he argues the latter to be manifest in IBM’s Smarter Planet campaign, which shapes the consumer’s world in anthropomorphic terms without explicitly making use of the rhetorical technique. Vested at the core of anthropomorphic technologies is the technique of photomontage, which has been prominent in both artistic and commercial imagery. In Photomontage and the Visual Language of Advertising: Two Reviews, Paul Messaris takes us through select episodes of its brief but insightful history, reviewing Photomontage between the Wars (1918–1939) by Adrian Sudhalter and Deborah L. Roldán, and John Heartfield and the Agitated Image: Photography, Persuasion, and the Rise of Avant-Garde Photomontage by Andrés Mario Zervigón. Artistic practices, as it transpires, have fundamentally shaped visual language in advertisements, once more blurring the distinctions between commercial and noncommercial expressions. After this foray into technologies of representation, it seems fitting to conclude the issue with a Classic Campaign that was both striking and provocative in its visual language and celebrity endorsement. MAC Cosmetics’ VIVA GLAM achieved fame by foregrounding artists RuPaul and k.d. lang as brand ambassadors, challenging both gender stereotypes and beauty conventions against the backdrop of the 1990s AIDS breakout. The campaign is testament to the ability of persuasive technologies to appeal to common humanities, and thereby not only achieve commercial success but, equally and concurrently, engender social impact. Copyright © 2013 The Advertising Educational Foundation, Inc

High‐Resolution Satellite Data Open for Government Research

U.S. satellite commercial imagery (CI) with resolution less than 1 meter is a common geospatial reference used by the public through Web applications, mobile devices, and the news media. However, CI use in the scientific community has not kept pace, even though those who are performing U.S. government research have access to these data at no cost. Previously, studies using multiple CI acquisitions from IKONOS‐2, Quickbird‐2, GeoEye‐1, WorldView‐1, and WorldView‐2 would have been cost prohibitive. Now, with near‐global submeter coverage and online distribution, opportunities abound for future scientific studies. This archive is already quite extensive (examples are shown in Figure 1) and is being used in many novel applications.