1) Data Introduction • The Satellite Image Classification Dataset is a benchmark image classification dataset constructed using satellite remote sensing imagery. It includes a total of four land surface classes—cloudy, desert, green_area, and water—collected from various sensor-based images and Google Maps snapshots. The dataset is designed for training and evaluating image-based scene recognition models.

2) Data Utilization (1) Characteristics of the Satellite Image Classification Dataset: • The dataset was collected with the aim of automatic interpretation of satellite imagery and consists of a combination of sensor-based images and map snapshots, offering a realistic representation of real-world conditions. • All images are of fixed resolution and include diverse landform features, making the dataset suitable for classification experiments across different environments and for evaluating model generalization performance.

(2) Applications of the Satellite Image Classification Dataset: • Land surface classification model training: Can be used in experiments to classify various types of terrain such as buildings, farmland, and roads. • Research and application in geospatial information analysis: Useful for developing models that support spatial decision-making through tasks such as land use monitoring, urban structure analysis, and land surface inference.

The global satellite imagery and image processing services market is experiencing robust growth, driven by increasing demand across diverse sectors. The market, estimated at $15 billion in 2025, is projected to expand at a Compound Annual Growth Rate (CAGR) of 7% from 2025 to 2033, reaching approximately $25 billion by 2033. This expansion is fueled by several key factors. Firstly, advancements in satellite technology are providing higher-resolution imagery with improved accuracy and faster processing times, enabling more detailed analysis for various applications. Secondly, the rising adoption of cloud-based platforms for image processing and analytics is streamlining workflows and reducing costs for users. This is particularly crucial for smaller businesses and organizations that previously lacked access to sophisticated image processing capabilities. Thirdly, the growing need for precise geographical information across diverse sectors, including environmental monitoring, precision agriculture, urban planning, and disaster response, fuels market demand. The defense and security sector remains a significant contributor, with increasing reliance on satellite imagery for intelligence gathering and surveillance. Market segmentation reveals significant opportunities within specific application areas. The environmental sector, utilizing satellite imagery for deforestation monitoring, climate change analysis, and pollution detection, is a rapidly growing segment. Similarly, the energy and power sector leverages satellite imagery for pipeline monitoring, renewable energy resource assessment, and infrastructure management. Within image processing types, the demand for advanced data analytics is soaring, with growing adoption of artificial intelligence and machine learning for automated feature extraction and predictive analysis. While regulatory hurdles and the high initial investment cost of satellite technologies pose some challenges, the overall market outlook remains positive, driven by technological advancements, increasing data accessibility, and rising demand for location-based intelligence. Competition is intensifying amongst established players and new entrants, leading to innovation and affordability in the market.

The satellite imagery and image processing market is expected to grow at a CAGR of XX% over the period of 2025-2033, reaching a value of million USD by 2033. The growing adoption of satellite imagery for various applications, such as environmental monitoring, defense and security, energy and power, and engineering and infrastructure, is driving the market growth. Additionally, the increasing demand for real-time data and the availability of advanced image processing techniques are further contributing to the market expansion. North America is expected to hold the largest market share over the forecast period, owing to the presence of key satellite imagery and image processing companies, such as L3Harris Technologies, Inc. and Satellite Imaging Corporation. The Asia Pacific region is projected to witness the highest growth rate during the forecast period, due to the growing demand for satellite imagery for applications such as agriculture and forestry, and the increasing investments in space exploration and satellite technology. Key players in the market include L3Harris Technologies, Inc., Satellite Imaging Corporation, Planet Labs Inc, Ursa Space Systems, Earth-I Ltd, and Satpalda Geospatial Services.

The Brazil Satellite Imagery Services Market report segments the industry into By Application (Geospatial Data Acquisition and Mapping, Natural Resource Management, Surveillance and Security, Conservation and Research, Disaster Management, Intelligence) and By End-User (Government, Construction, Transportation and Logistics, Military and Defense, Forestry and Agriculture, Other End-Users).

This repository contains the code and resources for the project titled "Detection of Areas with Human Vulnerability Using Public Satellite Images and Deep Learning". The goal of this project is to identify regions where individuals are living under precarious conditions and facing neglected basic needs, a situation often seen in Brazil. This concept is referred to as "human vulnerability" and is exemplified by families living in inadequate shelters or on the streets in both urban and rural areas.

Focusing on the Federal District of Brazil as the research area, this project aims to develop two novel public datasets consisting of satellite images. The datasets contain imagery captured at 50m and 100m scales, covering regions of human vulnerability, traditional areas, and improperly disposed waste sites.

The project also leverages these datasets for training deep learning models, including YOLOv7 and other state-of-the-art models, to perform image segmentation. A comparative analysis is conducted between the models using two training strategies: training from scratch with random weight initialization and fine-tuning using pre-trained weights through transfer learning.

• Two new satellite image datasets focusing on human vulnerability and improperly disposed waste sites, available in public domains.
• Comparison of image segmentation models, including YOLOv7 and Segmentation Models, with performance metrics.
• Best F1-scores: 0.55 for YOLOv7 and 0.64 for Segmentation Models.

This repository provides the code, models, and data pipelines used for training, evaluation, and performance comparison of these deep learning models.

@TECHREPORT {TechReport-Julia-Laura-HumanVulnerability-2024,
  author   = "Julia Passos Pontes, Laura Maciel Neves Franco, Flavio De Barros Vidal",
  title    = "Detecção de Áreas com Atividades de Vulnerabilidade Humana utilizando Imagens Públicas de Satélites e Aprendizagem Profunda",
  institution = "University of Brasilia",
  year    = "2024",
  type    = "Undergraduate Thesis",
  address   = "Computer Science Department - University of Brasilia - Asa Norte - Brasilia - DF, Brazil",
  month    = "aug",
  note    = "People living in precarious conditions and with their basic needs neglected is an unfortunate reality in Brazil. This scenario will be approached in this work according to the concept of \"human vulnerability\" and can be exemplified through families who live in inadequate shelters, without basic structures and on the streets of urban or rural centers. Therefore, assuming the Federal District as the research scope, this project proposes to develop two new databases to be made available publicly, considering the map scales of 50m and 100m, and composed by satellite images of human vulnerability areas,
regions treated as traditional and waste disposed inadequately. Furthermore, using these image bases, trainings were done with the YOLOv7 model and other deep learning models for image segmentation. By adopting an exploratory approach, this work compares the results of different image segmentation models and training strategies, using random weight initialization
(from scratch) and pre-trained weights (transfer learning). Thus, the present work was able to reach maximum F1
score values of 0.55 for YOLOv7 and 0.64 for other segmentation models."
}

This project is licensed under the MIT License - see the LICENSE file for details.

The KSA Satellite Imagery Services Market report segments the industry into By Application (Geospatial Data Acquisition and Mapping, Natural Resource Management, Surveillance and Security, Conservation and Research, Disaster Management, Intelligence) and By End-User (Government, Construction, Transportation and Logistics, Military and Defense, Forestry and Agriculture, Others).

The India Satellite Imagery Services Market report segments the industry into Application (Geospatial Data Acquisition and Mapping, Natural Resource Management, Surveillance and Security, Conservation and Research, Disaster Management, Intelligence) and End-User (Government, Construction, Transportation and Logistics, Military and Defense, Forestry and Agriculture, Others).

Dataset consists of SAR and Optical (RGB) image pairs from Sentinel‑1 and Sentinel‑2 satellites, provided by the Technical University of Munich. Sentinel-1&2 Image Pairs, Michael Schmitt, Technical University of Munich (TUM)

We searched through images captured during the fall season in the original dataset provided by TUM, and selected images which could belong to each of the four classes: barren land, grassland, agricultural land, and urban areas. Optical images shown in the following sections give an idea of the type of images belonging to each class. We have tried to introduced as much variation as possible when selecting images for a class.

Data can be used to train a Conditional GAN. Since the images in this dataset are highly complex i.e. they are not regularized and they do not have a neat geometric pattern or orientation, it can also be used to check the robustness of a model, no matter the task.

The Satellite Image Data Service Market is projected to reach $4.13 billion by 2033, exhibiting a CAGR of 8.34% during the forecast period (2025-2033). The market is driven by the increasing adoption of satellite imagery for various applications, including agriculture, urban planning, environmental monitoring, disaster management, and defense and intelligence. The growing need for accurate and real-time data for decision-making is further propelling the demand for satellite image data services. Key trends in the market include the rise of cloud-based delivery models, the development of advanced satellite technologies, and the integration of artificial intelligence (AI) and machine learning (ML) algorithms. Cloud-based platforms offer greater accessibility, scalability, and cost-efficiency, making satellite image data services more accessible to a wider range of users. Advanced satellite technologies, such as synthetic aperture radar (SAR), multispectral, and hyperspectral satellites, are enabling the capture of high-resolution and multi-dimensional data, providing deeper insights into various applications. The integration of AI and ML algorithms is enhancing the analysis and interpretation of satellite imagery, automating processes, and improving accuracy. Recent developments include: Recent developments in the Satellite Image Data Service Market reflect significant advancements and strategic movements among key players. Companies such as Esri, Maxar Technologies, and Planet Labs have seen notable increases in market demand fueled by the growing reliance on satellite imagery for various applications, including environmental monitoring, urban planning, and disaster management., Additionally, collaborations between organizations like NASA and the European Space Agency have focused on enhancing satellite data accessibility for both scientific and commercial use., Recent mergers and acquisitions have also shaped the landscape, with Raytheon and Northrop Grumman exploring opportunities to consolidate technologies for defense and monitoring applications. Furthermore, MDA and Airbus have been in discussions regarding partnerships to leverage satellite imagery for area-based assessments, enhancing service offerings., The financial health of companies like BlackSky has seen a boost as the market valuation increases, driven by rising awareness of the importance of spatial data in decision-making processes. The overall growth trajectory of the market indicates a shift towards integrated visual analytics and AI-driven insights, catering to diverse sectors actively seeking satellite data services.. Key drivers for this market are: AI integration for enhanced analysis, Increased demand for climate monitoring; Growth in defense and security applications; Expansion of remote sensing technologies; and Rising need for agricultural insights. Potential restraints include: Growing demand for imagery analytics, Advancements in satellite technology; Increasing use in agriculture; Rising environmental monitoring needs; and Expanding applications in defense.

This map shows the distribution of the iceberg data extracted from ERS SAR images.

Icebergs are identified in Synthetic Aperture Radar [SAR] images by image analysis using the texture and intensity of the microwave backscatter observations. The images are segmented using an edge detecting algorithm, and segments identified as iceberg or background, which may be sea ice, open water, or a mixture of both. Dimensions of the icebergs are derived by spatial analysis of the corresponding image segments. Location of the iceberg is derived from its position within the image and the navigation data that gives the location and orientation of the image.

More than 20,000 individual observations have been extracted from SAR images acquired by the European Space Agency's ERS-1 and 2 satellites and the Canadian Space Agency's Radarsat satellite. Because images can overlap, some proportion of the observations represent multiple observations of the same set of icebergs.

Most observations relate to the sector between longitudes 70E and 135E. The data set includes observations from several other discrete areas around the Antarctic coast. In general observations are within 200 km of the coast but in limited areas extend to about 500 km from the coast.

This metadata record has been derived from work performed under the auspices of ASAC project 2187 (ASAC_2187).

The map in the pdf file shows the extent of the coverage of individual SAR scenes used in the analysis and the abundance and size characteristics (by a limited colour palette) of the identified icebergs.

What is this dataset?

Nearly 10,000 km² of free high-resolution and matched low-resolution satellite imagery of unique locations which ensure stratified representation of all types of land-use across the world: from agriculture to ice caps, from forests to multiple urbanization densities.

Those locations are also enriched with typically under-represented locations in ML datasets: sites of humanitarian interest, illegal mining sites, and settlements of persons at risk.

Each high-resolution image (1.5 m/pixel) comes with multiple temporally-matched low-resolution images from the freely accessible lower-resolution Sentinel-2 satellites (10 m/pixel).

We accompany this dataset with a paper, datasheet for datasets and an open-source Python package to: rebuild or extend the WorldStrat dataset, train and infer baseline algorithms, and learn with abundant tutorials, all compatible with the popular EO-learn toolbox.

Why make this?

We hope to foster broad-spectrum applications of ML to satellite imagery, and possibly develop the same power of analysis allowed by costly private high-resolution imagery from free public low-resolution Sentinel2 imagery. We illustrate this specific point by training and releasing several highly compute-efficient baselines on the task of Multi-Frame Super-Resolution.

Licences

• The high-resolution Airbus imagery is distributed, with authorization from Airbus, under Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0).
• The labels, Sentinel2 imagery, and trained weights are released under Creative Commons with Attribution 4.0 International (CC BY 4.0).
• The source code (will be shortly released on GitHub) under 3-Clause BSD license.

The commercial satellite imaging market is set to accelerate from USD 5.87 billion in 2025 to USD 15.33 billion in 2035 at a 12.3% CAGR. New-generation constellations-Maxar’s 30 cm-class WorldView Legion, Planet’s high-revisit Pelican series and a wave of SAR microlaunches-are multiplying daily capture capacity while dropping per-kilometre image cost, opening analytics-ready feeds for agriculture, energy and insurance customers.

Attributes	Description
Estimated Size, 2025	USD 5.87 billion
Projected Size, 2035	USD 15.33 billion
Value-based CAGR (2025 to 2035)	12.3% CAGR

Semi-Annual Market Update

Particular	Value CAGR
H1 2024	11.6% (2024 to 2034)
H2 2024	11.8% (2024 to 2034)
H1 2025	12.3% (2025 to 2035)
H2 2025	12.6% (2025 to 2035)

Country-wise Insights

Countries	CAGR from 2025 to 2035
India	17.2%
China	15.8%
Germany	12.9%
Japan	13.0%
United States	13.7%

Analyzing Commercial Satellite Market by Top Investment Segments

Segment	CAGR (2025 to 2035)
Defense & Intelligence (Application)	11.7%

Segment	Value Share (2025)
Forestry & Agriculture (End User)	16.8%

The Commercial Satellite Imaging Market is Segmented by Application (Geospatial Data Acquisition and Mapping, and More), by End-User Vertical (Government, Construction, and More), by Imaging Type (Optical (Multispectral/Panchromatic and More), by Spatial Resolution (≤0. 3 M (Very-High), and More), by Orbit Class (Low-Earth Orbit (LEO) and More), and by Geography. The Market Forecasts are Provided in Terms of Value (USD).

Data was collected as part of the SOCPacific project. Dealing with challenges of the pandemic and travel restrictions, project participants aimed to develop a typology of reef passages based on visual interpretation of freely available satellite imagery. Nine islands of different sizes and shapes surrounded by coral reef structures were selected based on previous field expertise. Reef passages were mapped in GoogleEarth and further processed in QGIS (version 3.16) and R (version 3.5.3). In addition, outlines for the selected islands were downloaded from the GADM database (gadm.org). Parameters distance to coast, minimal width of the passage and the assigned type were added to the dataset. Passages were assigned one of three types defined in Breckwoldt et al. (in review) - Coastal, Lagoon or Open Ocean - depending on the geomorphological appearance of the reef and distance to the coast.

Dryland pastoralism has long attracted considerable attention from researchers in diverse fields. However, rigorous formal study is made difficult by the high level of mobility of pastoralists as well as by the sizable spatio-temporal variability of their environment. This article presents a new computational approach for studying mobile pastoralism that overcomes these issues. Combining multi-temporal satellite images and agent-based modeling allows a comprehensive examination of pastoral resource access over a realistic dryland landscape with unpredictable ecological dynamics. The article demonstrates the analytical potential of this approach through its application to mobile pastoralism in northeast Nigeria. Employing more than 100 satellite images of the area, extensive simulations are conducted under a wide array of circumstances, including different land-use constraints. The simulation results reveal complex dependencies of pastoral resource access on these circumstances along wit...

The Dynamic World Training Data is a dataset of over 5 billion pixels of human-labeled ESA Sentinel-2 satellite image, distributed over 24000 tiles collected from all over the world. The dataset is designed to train and validate automated land use and land cover mapping algorithms. The 10m resolution 5.1km-by-5.1km tiles are densely labeled using a ten category classification schema indicating general land use land cover categories. The dataset was created between 2019-08-01 and 2020-02-28, using satellite imagery observations from 2019, with approximately 10% of observations extending back to 2017 in very cloudy regions of the world. This dataset is a component of the National Geographic Society - Google - World Resources Institute Dynamic World project. […]

The first generation of U.S. photo intelligence satellites collected more than 860,000 images of the Earth’s surface between 1960 and 1972. The classified military satellite systems code-named CORONA, ARGON, and LANYARD acquired photographic images from space and returned the film to Earth for processing and analysis. The images were originally used for reconnaissance and to produce maps for U.S. intelligence agencies. In 1992, an Environmental Task Force evaluated the application of early satellite data for environmental studies. Since the CORONA, ARGON, and LANYARD data were no longer critical to national security and could be of historical value for global change research, the images were declassified by Executive Order 12951 in 1995. The first successful CORONA mission was launched from Vandenberg Air Force Base in 1960. The satellite acquired photographs with a telescopic camera system and loaded the exposed film into recovery capsules. The capsules or buckets were de-orbited and retrieved by aircraft while the capsules parachuted to earth. The exposed film was developed and the images were analyzed for a range of military applications. The intelligence community used Keyhole (KH) designators to describe system characteristics and accomplishments. The CORONA systems were designated KH-1, KH-2, KH-3, KH-4, KH-4A, and KH-4B. The ARGON systems used the designator KH-5 and the LANYARD systems used KH-6. Mission numbers were a means for indexing the imagery and associated collateral data. A variety of camera systems were used with the satellites. Early systems (KH-1, KH-2, KH-3, and KH-6) carried a single panoramic camera or a single frame camera (KH-5). The later systems (KH-4, KH-4A, and KH-4B) carried two panoramic cameras with a separation angle of 30° with one camera looking forward and the other looking aft. The original film and technical mission-related documents are maintained by the National Archives and Records Administration (NARA). Duplicate film sources held in the USGS EROS Center archive are used to produce digital copies of the imagery. Mathematical calculations based on camera operation and satellite path were used to approximate image coordinates. Since the accuracy of the coordinates varies according to the precision of information used for the derivation, users should inspect the preview image to verify that the area of interest is contained in the selected frame. Users should also note that the images have not been georeferenced.

The Middle East Satellite Imagery Services Market report segments the industry into Application (Geospatial Data Acquisition and Mapping, Natural Resource Management, Surveillance and Security, Conservation and Research, Disaster Management, Intelligence), End-User (Government, Construction, Transportation and Logistics, Military and Defense, Forestry and Agriculture, Other End-Users), and Geography (UAE, Saudi Arabia).

This dataset consists of annotated high-resolution aerial imagery of roof materials in Bonn, Germany, in the Ultralytics YOLO instance segmentation dataset format. Aerial imagery was sourced from OpenAerialMap, specifically from the Maxar Open Data Program. Roof material labels and building outlines were sourced from OpenStreetMap. Images and labels are split into training, validation, and test sets, meant for future machine learning models to be trained upon, for both building segmentation and roof type classification.The dataset is intended for applications such as informing studies on thermal efficiency, roof durability, heritage conservation, or socioeconomic analyses. There are six roof material types: roof tiles, tar paper, metal, concrete, gravel, and glass.Note: The data is in a .zip due to file upload limits. Please find a more detailed dataset description in the README.md

This dataset consists of collections of satellite image composites (Sentinel 2 and Landsat 8) that are created from manually curated image dates for a range of projects. These images are typically prepared for subsequent analysis or testing of analysis algorithms as part of other projects. This dataset acts as a repository of reproducible test sets of images processed from Google Earth Engine using a standardised workflow.

Details of the algorithms used to produce the imagery are described in the GEE code and code repository available on GitHub (https://github.com/eatlas/World_AIMS_Marine-satellite-imagery).


Project test image sets:

As new projects are added to this dataset, their details will be described here:

- NESP MaC 2.3 Benthic reflection estimation (projects/CS_NESP-MaC-2-3_AIMS_Benth-reflect):
This collection consists of six Sentinel 2 image composites in the Coral Sea and GBR for the purpose of testing a method of determining benthic reflectance of deep lagoonal areas of coral atolls. These image composites are in GeoTiff format, using 16-bit encoding and LZW compression. These images do not have internal image pyramids to save on space.
[Status: final and available for download]

- NESP MaC 2.3 Oceanic Vegetation (projects/CS_NESP-MaC-2-3_AIMS_Oceanic-veg):
This project is focused on mapping vegetation on the bottom of coral atolls in the Coral Sea. This collection consists of additional images of Ashmore Reef. The lagoonal area of Ashmore has low visibility due to coloured dissolved organic matter, making it very hard to distinguish areas that are covered in vegetation. These images were manually curated to best show the vegetation. While these are the best images in the Sentinel 2 series up to 2023, they are still not very good. Probably 80 - 90% of the lagoonal benthos is not visible.
[Status: final and available for download]

- NESP MaC 3.17 Australian reef mapping (projects/AU_NESP-MaC-3-17_AIMS_Reef-mapping):
This collection of test images was prepared to determine if creating a composite from manually curated image dates (corresponding to images with the clearest water) would produce a better composite than a fully automated composite based on cloud filtering. The automated composites are described in https://doi.org/10.26274/HD2Z-KM55. This test set also includes composites from low tide imagery. The images in this collection are not yet available for download as the collection of images that will be used in the analysis has not been finalised.
[Status: under development, code is available, but not rendered images]

- Capricorn Regional Map (projects/CapBunk_AIMS_Regional-map): This collection was developed for making a set of maps for the region to facilitate participatory mapping and reef restoration field work planning.
[Status: final and available for download]

- Default (project/default): This collection of manual selected scenes are those that were prepared for the Coral Sea and global areas to test the algorithms used in the developing of the original Google Earth Engine workflow. This can be a good starting point for new test sets. Note that the images described in the default project are not rendered and made available for download to save on storage space.
[Status: for reference, code is available, but not rendered images]


Filename conventions:

The images in this dataset are all named using a naming convention. An example file name is Wld_AIMS_Marine-sat-img_S2_NoSGC_Raw-B1-B4_54LZP.tif. The name is made up of:
- Dataset name (Wld_AIMS_Marine-sat-img), short for World, Australian Institute of Marine Science, Marine Satellite Imagery.
- Satellite source: L8 for Landsat 8 or S2 for Sentinel 2.
- Additional information or purpose: NoSGC - No sun glint correction, R1 best reference imagery set or R2 second reference imagery.
- Colour and contrast enhancement applied (DeepFalse, TrueColour,Shallow,Depth5m,Depth10m,Depth20m,Raw-B1-B4),
- Image tile (example: Sentinel 2 54LZP, Landsat 8 091086)


Limitations:

Only simple atmospheric correction is applied to land areas and as a result the imagery only approximates the bottom of atmosphere reflectance.

For the sentinel 2 imagery the sun glint correction algorithm transitions between different correction levels from deep water (B8) to shallow water (B11) and a fixed atmospheric correction for land (bright B8 areas). Slight errors in the tuning of these transitions can result in unnatural tonal steps in the transitions between these areas, particularly in very shallow areas.

For the Landsat 8 image processing land areas appear as black from the sun glint correction, which doesn't separately mask out the land. The code for the Landsat 8 imagery is less developed than for the Sentinel 2 imagery.

The depth contours are estimated using satellite derived bathymetry that is subject to errors caused by cloud artefacts, substrate darkness, water clarity, calibration issues and uncorrected tides. They were tuned in the clear waters of the Coral Sea. The depth contours in this dataset are RAW and contain many false positives due to clouds. They should not be used without additional dataset cleanup.



Change log:

As changes are made to the dataset, or additional image collections are added to the dataset then those changes will be recorded here.

2nd Edition, 2024-06-22: CapBunk_AIMS_Regional-map
1st Edition, 2024-03-18: Initial publication of the dataset, with CS_NESP-MaC-2-3_AIMS_Benth-reflect, CS_NESP-MaC-2-3_AIMS_Oceanic-veg and code for AU_NESP-MaC-3-17_AIMS_Reef-mapping and Default projects.


Data Format:

GeoTiff images with LZW compression. Most images do not have internal image pyramids to save on storage space. This makes rendering these images very slow in a desktop GIS. Pyramids should be added to improve performance.

Data Location:

This dataset is filed in the eAtlas enduring data repository at: data\custodian\2020-2029-AIMS\Wld-AIMS-Marine-sat-img