Military Aircraft Detection

Introduction #

T Nakamura

Authors introduce the Military Aircraft Detection Dataset, a comprehensive dataset designed for object detection of military aircraft. This dataset features bounding boxes in PASCAL VOC format (xmin, ymin, xmax, ymax) and includes images of 43 distinct aircraft types, such as A-10, F-35, Su-57, and more. The dataset, comprising 12,008 images in total, was sourced from Wikimedia Commons and Google Image Search, making it a valuable resource for training and evaluating object detection models for military aircraft recognition task.

Expand

Homepage

Summary #

Military Aircraft Detection is a dataset for an object detection task. Possible applications of the dataset could be in the security industry.

The dataset consists of 12008 images with 19270 labeled objects belonging to 43 different classes including F16, F15, F35, and other: F18, C2, C130, US2, V22, B1, A10, F4, C17, B2, F22, EF2000, B52, C5, JAS39, Rafale, A400M, E2, Vulcan, MQ9, AV8B, F14, Tornado, Be200, J20, RQ4, U2, Su34, SR71, Mirage2000, Mig31, Tu160, AG600, Su57, F117, Tu95, P3, XB70, E7, and YF23.

Images in the Military Aircraft Detection dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are no pre-defined train/val/test splits in the dataset. The dataset was released in 2020.

Here is a visualized example for randomly selected sample classes:

Explore #

Military Aircraft Detection dataset has 12008 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 Military Aircraft Detection

Sample image from Military Aircraft Detection

👀

Have a look at 12008 images

Because of dataset's license preview is limited to 12 images

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

Class balance #

There are 43 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 1-10 of 43

Class ㅤ	Images ㅤ	Objects ㅤ	Count on image average	Area on image average
F16➔ rectangle	706	1155	1.64	24.83%
F15➔ rectangle	668	1116	1.67	25.5%
F35➔ rectangle	660	976	1.48	18.37%
F18➔ rectangle	574	1163	2.03	24.35%
C2➔ rectangle	569	715	1.26	32.89%
C130➔ rectangle	563	814	1.45	19.38%
US2➔ rectangle	517	570	1.1	19.85%
V22➔ rectangle	487	734	1.51	19.23%
B1➔ rectangle	380	535	1.41	22.24%
A10➔ rectangle	372	567	1.52	17.59%

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.

Object distribution #

Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.

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 1-10 of 43

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
F18 rectangle	1163	12.61%	99.94%	0.01%	10px	0.76%	2725px	99.96%	310px	22.57%	14px	1.09%	5317px	99.98%
F16 rectangle	1155	15.97%	99.94%	0.02%	10px	1.22%	4095px	99.98%	397px	27.64%	17px	1.32%	5840px	99.98%
F15 rectangle	1116	15.66%	99.96%	0.01%	8px	1.12%	4095px	99.98%	340px	26.12%	12px	1.2%	6015px	99.98%
F35 rectangle	976	12.67%	99.94%	0.02%	9px	1.12%	4095px	99.98%	320px	23.42%	18px	1.3%	4458px	99.98%
C130 rectangle	814	13.68%	99.94%	0%	9px	0.44%	4095px	99.98%	326px	22.95%	22px	0.76%	6047px	99.98%
V22 rectangle	734	13.17%	99.88%	0.02%	10px	0.97%	2760px	99.93%	282px	22.65%	17px	1.42%	5475px	99.98%
C2 rectangle	715	26.76%	99.86%	0.05%	12px	1.76%	3890px	99.92%	352px	36.96%	15px	2.93%	6047px	99.98%
US2 rectangle	570	18.29%	99.93%	0.04%	13px	1.3%	3909px	99.96%	272px	27.4%	25px	2.08%	5817px	99.98%
A10 rectangle	567	11.77%	99.95%	0.03%	12px	1.33%	3187px	99.97%	319px	21.94%	25px	1.22%	4927px	99.98%
F22 rectangle	552	12.14%	99.94%	0.01%	12px	0.55%	3858px	99.96%	333px	23.85%	31px	0.95%	6876px	99.99%

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 19270 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 19270

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➔	F18 rectangle	d26599941d61aa42ea763e9abf4818c7.jpg	2048 x 2048	1593px	77.78%	1108px	54.1%	42.08%
2➔	J20 rectangle	c5daa1bd8440d29c8f4027bef9017ac1.jpg	540 x 960	118px	21.85%	73px	7.6%	1.66%
3➔	J20 rectangle	c5daa1bd8440d29c8f4027bef9017ac1.jpg	540 x 960	80px	14.81%	65px	6.77%	1%
4➔	Mig31 rectangle	cc4aa960860c8da40240d319ea6f5f76.jpg	1602 x 1068	577px	36.02%	897px	83.99%	30.25%
5➔	Mig31 rectangle	cc4aa960860c8da40240d319ea6f5f76.jpg	1602 x 1068	443px	27.65%	683px	63.95%	17.68%
6➔	Vulcan rectangle	8f5afc820a07f70a96bf34ee43abd30d.jpg	665 x 1024	294px	44.21%	1023px	99.9%	44.17%
7➔	AV8B rectangle	1fb5e5615223d27cd04be61033a8b06d.jpg	2048 x 1710	298px	14.55%	554px	32.4%	4.71%
8➔	EF2000 rectangle	e77db44803b33494f10221413b3274d2.jpg	1281 x 1920	436px	34.04%	1301px	67.76%	23.06%
9➔	EF2000 rectangle	e77db44803b33494f10221413b3274d2.jpg	1281 x 1920	513px	40.05%	1477px	76.93%	30.81%
10➔	F16 rectangle	7f865c2a1fb9a5c8ba1ce308d52e1ed9.jpg	1333 x 2000	463px	34.73%	983px	49.15%	17.07%

License #

License is unknown for the Military Aircraft Detection dataset.

Source

Citation #

If you make use of the Military Aircraft Detection data, please cite the following reference:

@dataset{Military Aircraft Detection,
  author={T Nakamura},
  title={Military Aircraft Detection},
  year={2020},
  url={https://www.kaggle.com/datasets/a2015003713/militaryaircraftdetectiondataset}
}

Source

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

@misc{ visualization-tools-for-military-aircraft-detection-dataset,
  title = { Visualization Tools for Military Aircraft Detection Dataset },
  type = { Computer Vision Tools },
  author = { Dataset Ninja },
  howpublished = { \url{ https://datasetninja.com/military-aircraft-detection } },
  url = { https://datasetninja.com/military-aircraft-detection },
  journal = { Dataset Ninja },
  publisher = { Dataset Ninja },
  year = { 2024 },
  month = { nov },
  note = { visited on 2024-11-21 },
}

Download #

Please visit dataset homepage to download the data.

. . .

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.