Airbus Oil Storage Detection

Introduction #

Jeff Faudi

The Airbus Oil Storage Detection Sample Dataset is a subset derived from larger deep learning datasets developed using Airbus satellite imagery. The authors of the dataset present this version for illustrative purposes. The dataset aims to showcase the capabilities of Deep Learning in automatically detecting characteristics of Aboveground Petroleum, Oil and Lubricant (POL) storage areas, including the number, size, and type of POL storage on various sites. This automated detection contributes to monitoring the condition of aboveground fuel storage tanks, facilitating tasks such as spill prevention, overfill prevention, and corrosion monitoring.

Airbus Defense and Space Intelligence, a key player in commercial satellite imaging, operates the largest commercial satellite constellation, integrating optical imagery from Pléiades, SPOT, Vision-1, and DMC, along with radar imagery from TerraSAR-X, TanDEM-X, and PAZ. The authors are continually enhancing their sensor capabilities through the upcoming Pléiades Neo constellation, which offers higher resolution, increased revisits, and expanded acquisition capabilities. The OneAtlas platform provides a user-friendly gateway to Airbus’ premium satellite imagery, innovative geospatial analytics, and industry-specific insights.

The dataset comprises 98 image extracts from SPOT imagery, each at approximately 1.2 meters resolution. These images are stored as JPEG files with dimensions of 2560 x 2560 pixels, which corresponds to an area of 3 kilometers on the ground. The dataset encompasses locations worldwide, ensuring diversity.

Thorough annotations have been provided for all POL storage areas within the provided imagery. These annotations are represented as closed GeoJSON polygons.

Expand

Homepage

Summary #

Sample Oil Storage Tank Detection Dataset from Airbus SPOT Satellite Imagery is a dataset for an object detection task. It is used in the aviation industry.

The dataset consists of 103 images with 13592 labeled objects belonging to 1 single class (oil-storage-tank).

Images in the Airbus Oil Storage Detection dataset have bounding box annotations. There are 5 (5% of the total) unlabeled images (i.e. without annotations). There are 2 splits in the dataset: images (98 images) and extras (5 images). The dataset was released in 2021 by the Airbus DS Intelligence.

Explore #

Airbus Oil Storage Detection dataset has 103 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.

Sample annotation mask from Airbus Oil Storage Detection

Sample image from Airbus Oil Storage Detection

👀

Have a look at 103 images

View images along with annotations and tags, search and filter by various parameters

Class balance #

There are 1 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.

Rows 1-1 of 1

Class ㅤ	Images ㅤ	Objects ㅤ	Count on image average	Area on image average
oil-storage-tank➔ rectangle	98	13592	138.69	1.84%

Images #

Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.

Class sizes #

The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.

Rows 1-1 of 1

Class	Object count	Avg area	Max area	Min area	Min height	Min height	Max height	Max height	Avg height	Avg height	Min width	Min width	Max width	Max width
oil-storage-tank rectangle	13592	0.01%	0.19%	0%	1px	0.04%	115px	4.49%	25px	0.96%	3px	0.12%	109px	4.26%

Spatial Heatmap #

The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.

Objects #

Table contains all 13592 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.

Rows 1-10 of 13592

Object ID ㅤ	Class ㅤ	Image name click row to open	Image size height x width	Height ㅤ	Height ㅤ	Width ㅤ	Width ㅤ	Area ㅤ
1➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	20px	0.78%	22px	0.86%	0.01%
2➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	19px	0.74%	22px	0.86%	0.01%
3➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	20px	0.78%	21px	0.82%	0.01%
4➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	21px	0.82%	19px	0.74%	0.01%
5➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	19px	0.74%	23px	0.9%	0.01%
6➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	22px	0.86%	20px	0.78%	0.01%
7➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	11px	0.43%	13px	0.51%	0%
8➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	18px	0.7%	18px	0.7%	0%
9➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	19px	0.74%	19px	0.74%	0.01%
10➔	oil-storage-tank rectangle	37bd2972-fecb-48c8-8b1c-a7476a28d808.jpg	2560 x 2560	13px	0.51%	12px	0.47%	0%

License #

Sample Oil Storage Tank Detection Dataset from Airbus SPOT Satellite Imagery is under CC BY-NC-SA 4.0 license.

Source

Citation #

If you make use of the Airbus Oil Storage Detection data, please cite the following reference:

@dataset{Airbus Oil Storage Detection,
	author={Jeff Faudi},
	title={Sample Oil Storage Tank Detection Dataset from Airbus SPOT Satellite Imagery},
	year={2021},
	url={https://www.kaggle.com/datasets/airbusgeo/airbus-oil-storage-detection-dataset}
}

Source

If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:

@misc{ visualization-tools-for-airbus-oil-storage-detection-dataset,
  title = { Visualization Tools for Airbus Oil Storage Detection Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/airbus-oil-storage-detection } },
  url = { https://datasetninja.com/airbus-oil-storage-detection },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { jul },
  note = { visited on 2024-07-27 },
}

Download #

Dataset Airbus Oil Storage Detection can be downloaded in Supervisely format:

As an alternative, it can be downloaded with dataset-tools package:

pip install --upgrade dataset-tools

… using following python code:

import dataset_tools as dtools

dtools.download(dataset='Airbus Oil Storage Detection', dst_dir='~/dataset-ninja/')

Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.

The data in original format can be downloaded here.

. . .

Disclaimer #

Our gal from the legal dep told us we need to post this:

Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.

You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.