AI tool for the
indoor sports

Stellis Spark
Sports Camera
with AI.

Fully automated AI tools provide world leading technologies at affordable prices. Based on collected data, video tracking, video analysis and insights, reachable from Smartphone and Sport Cameras.

It uses Optical Based Tracking System – self-learning deep neural networks that give a fully automated way of obtaining statistics from a match recording. The system can be used by clubs, coaches, players, scouts and media, from lower leagues to professional clubs.

Computer Vision

Acquiring, processing and analyzing video image to understand more about the play.

Deep learning

Technology of performing machine learning inspired by human brain network of neurons to learn about the play.


Self learning deep neural networks that give a fully automatic way of obtaining statistics from a match recording

Optical Based Tracking System

According to FIFA classification of Electronic Performance and Tracking Systems.

Video tracking

Algorithms allowing detecting players
and ball movement to show statistics
of individual players over time.

ISVP.AI R&D stages of preparation

Training dataset based on football matches videos:

  • marking ball goals, referee or referees, players on each frame of the match recorded in real condition 

Match recordings preprocessing module: 

  • dividing video into single frames
  • detection of field, filtering out irrelevant fragments 

Target architecture of ISVP.Al system:

  • based on cloud services (Amazon, Google or Microsoft or suppliers focused on solutions using machine learning).

Training of the selected algorithms:

  • training with the entire training dataset based on the target architecture

Image instance segmentation module:

  • detecting goal gates, players and ball on each frame of the video + based on convolutional neural networks

Initial training of the chosen neural network architectures:

  • training only on a subset of the total training dataset 
  • calculations performed on the GPU 

Detected people objects classification module:

  • assigning classes of the players and other objects . classifying players to the teams

Preparation of a web application:

  • possibility of uploading the match recording by the target recipient  
  • analysis using the ISVP.Al engine
  • presentation of a produced video 

Optimizations in the source code:

  • improving system performance and efficiency by adjusting hyperparameters of the system or rewriting computationally demanding pieces of code in C language

Movement tracking:

  • tracking the location of objects from the first frame. 
  • redetection of the objects (by neural network) In case the video tracking mechanism fails

Detection of football match events:

  • the beginning and the end of the match, the first and second half and unplanned breaks

Thanks to the generous support of NCBiR (National Center for Research and Development)

We conducted R&D works on the development of a prototype of the AI system to make the production of recordings of indoor sport matches automated.

The aim of the project is to:

  • produce visually attractive recordings
  • generate action shortcuts
  • generate basic match statistics

The final product will be targeted at:





Lower leagues


Project value:

2 101 010.00

European Funds Contribution:

1 616 272.75

Tools for sport
industry experts
that think differently

Join our contellation and book a demo