Introduction
The aim of this dataset is to aid the development and evaluation of computer vision algorithms, primarily the radial distortion correction algorithms, in the sports domain.
This dataset contains 268 panorama images, and was created using the PANONO panoramic camera in 3 football arenas in Slovakia. Each arena was covered from numerous locations on all levels of the tribune, and broadcast camera platforms. The images capture regular football game, pitch maintenance, low/challenging lighting conditions, day and night situations.
| Arena | Number of images |
|---|---|
| Bratislava | 111 |
| Trnava | 104 |
| Dunajská Streda | 53 |
You can download the raw images from the following link – football360-raw.tar.gz (7.7 GB)
There is also an official GitHub repository available at – https://github.com/IgorJanos/stuFootball360
The original paper can be found here – https://www.scitepress.org/PublishedPapers/2023/116812/116812.pdf
Raw Images
Raw images are stored as 16384×8192 JPG, they are the direct result of the PANONO stitching service.
Exported Sets
There are four exported datasets available for direct download and use. Each dataset contains a collection of images (data) distorted with known distortion coefficients (labels).
| Set name | Purpose | Images | Preset | Download Link |
|---|---|---|---|---|
| A | Training | 30,000 | setA.json | football360-setA.h5 (10.5 GB) |
| B | Training | 100,000 | setB.json | football360-setB.h5 (35.2 GB) |
| C | Training | 300,000 | setC.json | football360-setC.h5 (105.5 GB) |
| V | Validation | 10,000 | setV.json | football360-setV.h5 (3.5 GB) |
You can see an example of how to load and use these files in a linked notebook – https://github.com/IgorJanos/stuFootball360/blob/main/notebooks/explore.ipynb
| Distorted Image | Corrected Image |
|---|---|
 |
|
 |
|
 |
|
 |
|
 |
|