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.

Context The Bhuvan Satellite Dataset is a valuable resource for land cover analysis and segmentation tasks. It includes a collection of satellite images and corresponding segmentation masks. The segmentation masks provide a pixel-level classification for five distinct land cover classes: vegetation, urban areas, forest, water bodies, and roads.

Content The dataset consists of satellite 2D images of Varanasi, a city located in the northern part of India, in the state of Uttar Pradesh, with coordinates ranging from 25.3° to 25.5° N latitude and 83° to 83.2° E longitude. It comprises a collection of high-resolution images capturing the Earth's surface. These images were obtained from the Indian Remote Sensing Satellite (IRS) and were processed and made available through the Bhuvan Geo Platform, which is managed by the Indian Space Research Organization (ISRO).

The dataset includes various files that offer valuable insights into the land cover classification and segmentation tasks. Here are the different data files available:

1. pixel_based_mask: This file contains pixel-level segmentation masks that classify each pixel in the satellite images into one of the land cover classes, such as vegetation, urban areas, forest, water bodies, and roads.
2. test_mask and train_mask: These files contain the manually generated segmentation masks specifically for creating the pixel-based mask.
3. test_image and train_image: These files contain the corresponding satellite images that are used for testing and training the land cover classification models. These high-resolution 2D images provide visual information about the Earth's surface in Varanasi.
4. class_dict_seg.csv: This file serves as a reference for the class labels used in the segmentation masks. It provides a mapping between the class names and their corresponding numeric labels in RGB format.

Researchers and professionals can leverage this dataset to conduct in-depth analysis and segmentation tasks related to land cover classification. The dataset's rich content enables the exploration of urban development, vegetation patterns, forest cover, water resources, and road networks within the Varanasi region.

Acknowledgements We would like to express our gratitude to Bhuvan - India Geo Platform of ISRO for providing the satellite images, which serve as a valuable resource for land cover analysis. We appreciate their efforts in collecting and curating satellite images, enabling researchers and professionals to explore and advance their work in remote sensing and geospatial analysis.

Inspiration Artificial Intelligence, Computer Vision, Image Processing, Deep Learning, Machine Learning, Satellite Image, Remote Sensing

CoastSat image classification training data

CoastSat is an open-source global shoreline mapping toolbox, available at https://github.com/kvos/CoastSat, which enables users to extract time-series of shoreline change from 30+ years of publicly available satellite imagery (Landsat 5, 7, 8 and Sentinel-2).

The automated shoreline extraction relies on a classifier (Multilayer Perceptron from scikit-learn) which labels each pixels on the images with one of four classes: sand, water, white-water and other land features.

The data used to train the classifier is stored here, the README.md file provides information on the data organisation and content of each file.

About Dataset

This dataset is designed for binary classification tasks on geospatial imagery, specifically to distinguish between land areas with trees and those without. The images were captured by the Sentinel-2 satellite.

The dataset structure is straightforward: - Each image has a resolution of 64×64 pixels with encoded in JPG format. - Images are organized into two folders: "Trees" and "NoTrees", corresponding to the two classes. - Each folder contains 5,200 images, totaling 10,400 images across the dataset.

Note: The dataset does not include predefined training, validation, or test splits. Users should partition the data as needed for their specific machine learning, deep learning workflows.

And you can also cite the source of this data EUROSAT: Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019). Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7), 2217-2226.

Context

Satellite image Classification Dataset-RSI-CB256 , This dataset has 4 different classes mixed from Sensors and google map snapshot

Content

The past years have witnessed great progress on remote sensing (RS) image interpretation and its wide applications. With RS images becoming more accessible than ever before, there is an increasing demand for the automatic interpretation of these images. In this context, the benchmark datasets serve as essential prerequisites for developing and testing intelligent interpretation algorithms. After reviewing existing benchmark datasets in the research community of RS image interpretation, this article discusses the problem of how to efficiently prepare a suitable benchmark dataset for RS image interpretation. Specifically, we first analyze the current challenges of developing intelligent algorithms for RS image interpretation with bibliometric investigations. We then present the general guidance on creating benchmark datasets in efficient manners. Following the presented guidance, we also provide an example on building RS image dataset, i.e., Million-AID, a new large-scale benchmark dataset containing a million instances for RS image scene classification. Several challenges and perspectives in RS image annotation are finally discussed to facilitate the research in benchmark dataset construction. We do hope this paper will provide the RS community an overall perspective on constructing large-scale and practical image datasets for further research, especially data-driven ones.

Acknowledgements

Annotated Datasets for RS Image Interpretation The interpretation of RS images has been playing an increasingly important role in a large diversity of applications, and thus, has attracted remarkable research attentions. Consequently, various datasets have been built to advance the development of interpretation algorithms for RS images. Covering literature published over the past decade, we perform a systematic review of the existing RS image datasets concerning the current mainstream of RS image interpretation tasks, including scene classification, object detection, semantic segmentation and change detection.

Inspiration

Artificial Intelligence, Computer Vision, Image Processing, Deep Learning, Satellite Image, Remote Sensing

This dataset contains satellite images categorized into 21 classes such as buildings, baseball fields, and freeways. Images are 256×256 pixels, augmented to provide 500 samples per class for robust machine learning model development.

This dataset consists of 1,759,830 multi-spectral image patches from the Sentinel-2 mission, annotated with image- and pixel-level land cover and land usage labels from the German land cover model LBM-DE2018 with land cover classes based on the CORINE Land Cover database (CLC) 2018. It includes pixel synchronous examples from each of the four seasons, plus an additional snowy set, spanning the time from April 2018 to February 2019. The patches were taken from 519,547 unique locations, covering the whole surface area of Germany, with each patch covering an area of 1.2km x 1.2km. The set is split into two overlapping grids, consisting of roughly 880,000 samples each, which are shifted by half the patch size in both dimensions. The images in each of the both grids themselves do not overlap.

Contents

Each sample includes:

• 3 10m resolution bands (RGB), 120px x 120px
• 1 10m resolution band (infrared), 120px x 120px
• 6 20m resolution bands, 60px x 60px
• 2 60m resolution bands, 20xp x 20px
• 1 pixel-level label map
• 2 binary masks for cloud and snow coverage
• 2 binary masks for easy and medium segmentation difficulties, marks areas <300px and <100px respectively
• 1 JSON-file containing additional meta-information

The meta.csv contains the following information about each sample:

• Which season it belongs to
• Which of the two grids it belongs to
• Coordinates of the patch center
• Whether it was acquired from Sentinel-2 Satellite A or B
• Date and time of image acquisition
• Snow and cloud coverage percentages
• Image-level multi-class labels
• Three additional image-level urbanization labels, based on the center pixel (details below)
• The path to the sample

Classes

ID	Class
1	Continuous urban fabric
2	Discontinuous urban fabric
3	Industrial or commercial units
4	Road and rail networks and associated land
5	Port areas
6	Airports
7	Mineral extraction sites
8	Dump sites
9	Construction sites
10	Green urban areas
11	Sport and leisure facilities
12	Non-irrigated arable land
13	Vineyards
14	Fruit trees and berry plantations
15	Pastures
16	Broad-leaved forest
17	Coniferous forest
18	Mixed forest
19	Natural grasslands
20	Moors and heathland
21	Transitional woodland/shrub
22	Beaches, dunes, sands
23	Bare rock
24	Sparsely vegetated areas
25	Inland marshes
26	Peat bogs
27	Salt marshes
28	Intertidal flats
29	Water courses
30	Water bodies
31	Coastal lagoons
32	Estuaries
33	Sea and ocean

Urbanization classes

• SLRAUM
  • 0: None
  • 1: Ländlicher Raum (~ rural area)
  • 2: Städtischer Raum (~ urban area)
• RTYP3
  • 0: None
  • 1: Ländliche Regionen (~ rural areas)
  • 2: Regionen mit Verstädterungsansätzen (~ urbanizing areas)
  • 3: Städtische Regionen (~ urban areas)
• KTYP4
  • 0: None
  • 1: Dünn besiedelte ländliche Kreise
  • 2: Kreisfreie Großstädte
  • 3: Ländliche Kreise mit Verdichtungsansätzen
  • 4: Städtische Kreise

Further information on the urbanization classes can be found here:

SLRAUM

https://www.bbsr.bund.de/BBSR/DE/forschung/raumbeobachtung/Raumabgrenzungen/deutschland/kreise/staedtischer-laendlicher-raum/kreistypen.html

RTYP3

https://www.bbsr.bund.de/BBSR/DE/forschung/raumbeobachtung/Raumabgrenzungen/deutschland/regionen/siedlungsstrukturelle-regionstypen/regionstypen.html

KTYP4

https://www.bbsr.bund.de/BBSR/DE/forschung/raumbeobachtung/Raumabgrenzungen/deutschland/kreise/siedlungsstrukturelle-kreistypen/kreistypen.html

License of landcover model

Bundesamt für Kartographie und Geodäsie

dl-de/by-2-0 from https://www.govdata.de/dl-de/by-2-0

© GeoBasis-DE / BKG 2022

Source of landcover model

https://gdz.bkg.bund.de/index.php/default/catalog/product/view/id/1071/s/corine-land-cover-5-ha-stand-2018-clc5-2018/

1) Data Introduction • The Land-Use Scene Classification Dataset is an image dataset built to classify land-use types in different regions based on Landsat satellite imagery.

2) Data Utilization (1) Characteristics of the Land-Use Scene Classification Dataset: • The images are collected from a diverse range of geographic environments, including urban, rural, coastal, and forested areas, making the dataset suitable for evaluating domain generalization performance. • It is based on low-resolution Landsat satellite images, yet designed to effectively distinguish various terrain and structural patterns even with limited spatial resolution.

(2) Applications of the Land-Use Scene Classification Dataset: • Development of land-use classification models: The dataset can be used to train deep learning models that automatically classify land-use types such as residential areas, roads, and farmlands from satellite imagery. • GIS-based land-use change analysis: It can support geographic information system (GIS) research to analyze land-use pattern changes over time and infer spatial utilization trends.

The imagery is downloaded from Google Earth Engine (GEE). It is the Sentinel 2 MSI dataset. The label data is generated based on the Nepal water bodies' shapefile.

1) Data Introduction • The Wildfire Prediction Dataset is a satellite image classification dataset constructed based on historical wildfire occurrences in Canada. The dataset consists of two classes: ‘wildfire’ (presence of wildfire) and ‘no_wildfire’ (absence of wildfire).

2) Data Utilization (1) Characteristics of the Wildfire Prediction Dataset: • Each image was extracted from satellite data using the latitude and longitude coordinates of actual wildfire locations. The dataset is designed for training deep learning models to predict the likelihood of wildfire occurrence.

(2) Applications of the Wildfire Prediction Dataset: • Development of wildfire risk prediction models: The dataset can be used to train AI models that classify whether a given region is at risk of wildfire based on satellite imagery. • Environmental monitoring and disaster response system research: Useful for building satellite-based wildfire monitoring systems that take into account climate change, terrain, and vegetation conditions.

This dataset is part of the larger data collection, “Aerial imagery object identification dataset for building and road detection, and building height estimation”, linked to in the references below and can be accessed here: https://dx.doi.org/10.6084/m9.figshare.c.3290519. For a full description of the data, please see the metadata: https://dx.doi.org/10.6084/m9.figshare.3504413.

Imagery data from the United States Geological Survey (USGS); building and road shapefiles are from OpenStreetMaps (OSM) (these OSM data are made available under the Open Database License: http://opendatacommons.org/licenses/odbl/1.0/); and the Lidar data are from U.S. National Oceanic and Atmospheric Administration (NOAA), the Texas Natural Resources Information System (TNRIS).

The ARGO ship classification dataset holds 1750 labelled images from PlanetScope-4-Band satelites. The dataset creation process and results on the dataset are published in the demo paper:

{CITE}

The imagery is provided as numpy binary files. All image data is licensed by Planet Labs PBC. The channel ordering is BGRN. The dataset is provided in two folders named "ship" and "non_ship". Those folders correspond to the original labels created during automated dataset creation. The files are numbered.

Two additional .csv files are provided. The shipsAIS_2017_Zone17.csv file holds the AIS information on the imagery contained in the ship folder. The data was retrieved from marinecadastre.gov.

During the experiments errors in the automatically created dataset emerged which are further described in the paper. The manual relabelling is supplied in the corrected_labels.csv file.

EuroSAT is a land use and land cover classification dataset. The dataset is based on Sentinel-2 satellite imagery covering 13 spectral bands and consists of 10 LULC classes with a total of 27,000 labeled and geo-referenced images. The dataset is associated with the publications "Introducing EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification" and "EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification".

EuroSAT_RGB.zip contains the RGB version of the dataset, which includes the optical R, G and B frequency bands encoded as JPEG images.

EuroSAT_MS.zip contains the multi-spectral version of the EuroSAT dataset, which includes all 13 Sentinel-2 bands in the original value range.

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 combines high-resolution satellite imagery from three distinct sources into a unified resource for advanced semantic segmentation tasks. It features a total of 203 images, meticulously annotated to identify six key classes:

1. Building: #3C1098
2. Land (unpaved area): #8429F6
3. Road: #6EC1E4
4. Vegetation: #FEDD3A
5. Water: #E2A929
6. Unlabeled: #9B9B9B
7. Object

The images span diverse urban and natural environments, providing a rich basis for developing and testing segmentation models. The standardized labels and masks facilitate straightforward application in machine learning projects aimed at urban planning, environmental monitoring, and beyond.

This dataset was created by joining 3 different datasets; 1. Semantic segmentation of aerial imagery 2. Land Cover Classification : Bhuvan Satellite Data 3. Urban Segmentation - ISPRS

I joined the datasets and standardized the masks so they have same color codings. And you can see the data yourself. Dive into the data and discover its potential for your projects!

The DeepGlobe Land Cover Classification Dataset is widely used in remote sensing and computer vision for training machine learning models to classify different land cover types such as urban areas, forests, water, and agriculture.

Satellite data and aerial photos have proved to be useful in efficient conservation and management of mangrove ecosystems. However, there have been only very few attempts to demonstrate the ability of drone images, and none so far to observe vegetation (species-level) mapping. The present study compares the utility of drone images (DJI-Phantom-2 with SJ4000 RGB and IR cameras, spatial resolution: 5cm) and satellite images (Pleiades-1B, spatial resolution: 50cm) for mangrove mapping—specifically in terms of image quality, efficiency and classification accuracy, at the Setiu Wetland in Malaysia. Both object- and pixel-based classification approaches were tested (QGIS v.2.12.3 with Orfeo Toolbox). The object-based classification (using a manual rule-set algorithm) of drone imagery with dominant land-cover features (i.e. water, land, Avicennia alba, Nypa fruticans, Rhizophora apiculata and Casuarina equisetifolia) provided the highest accuracy (overall accuracy (OA): 94.0±0.5% and specific producer accuracy (SPA): 97.0±9.3%) as compared to the Pleiades imagery (OA: 72.2±2.7% and SPA: 51.9±22.7%). In addition, the pixel-based classification (using a maximum likelihood algorithm) of drone imagery provided better accuracy (OA: 90.0±1.9% and SPA: 87.2±5.1%) compared to the Pleiades (OA: 82.8±3.5% and SPA: 80.4±14.3%). Nevertheless, the drone provided higher temporal resolution images, even on cloudy days, an exceptional benefit when working in a humid tropical climate. In terms of the user-costs, drone costs are much higher, but this becomes advantageous over satellite data for long-term monitoring of a small area. Due to the large data size of the drone imagery, its processing time was about ten times greater than that of the satellite image, and varied according to the various image processing techniques employed (in pixel-based classification, drone >50 hours, Pleiades

Yearly citation counts for the publication titled "Improving satellite image classification accuracy using GAN-based data augmentation and vision transformers".

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.

1) Data Introduction • The Satellite Images of Hurricane Damage Dataset is The Satellite Images of Hurricane Damage Dataset is a binary image classification computer vision dataset based on satellite images taken in Texas, USA, after Hurricane Harvey in 2017. Each image is labeled as either ‘damage’ (indicating structural damage) or ‘no_damage’ (indicating no damage), allowing for automatic identification of building damage in disaster scenarios.

2) Data Utilization (1) Characteristics of the Satellite Images of Hurricane Damage Dataset: • The dataset is composed of real satellite images taken immediately after a natural disaster, providing a realistic and reliable training environment for the development of automated disaster response and recovery systems.

(2) Applications of the Satellite Images of Hurricane Damage Dataset: • Development of disaster damage recognition models: This dataset can be used to train deep learning-based AI models that automatically classify whether buildings have been damaged based on satellite imagery. These models can contribute to decision-making in rescue prioritization and damage extent analysis. • Geospatial risk prediction systems: By integrating with GIS systems, the dataset can help visualize damage-prone areas on maps, supporting real-time decisions and resource allocation optimization during future disasters.