About Us
We are a group of young researchers and students from top rank university of Iran with a passion for creativity which is a basis for a brighter future. Our team is working on soccer match analysis using machine learning algorithms.
Our Mission
Given the fact that soccer is the most popular sport in the world, our ultimate goal is to develop optimized software that automatically analyzes the soccer matches and extracts the highlights and players’ statistics which would be of interest of soccer technical analyzers.
Our Plan
We believe that Machine learning will pave the way to analyze the sport automatically and our plan is to create or utilize different data mining tools that make this possible.
Our Vision
We treat data as a pivotal asset to our team and combine the knowledge and collaborative explosion of creativity to extract significant information which is the basis for a brighter future.
Services
Our services contain a broad range of soccer data analysis from providing multimodal datasets (image, video and sounds) to advanced components such as event detection, virtual advertising and keyword spotting.
Virtual Advertising
Using this service, you can advertise your product or service on the stadium billboards virtually and completely by a single software. Another service you can use is overlaying flags and logos of teams or any other picture you want on the grass.
Event Detection
Soccer event detection is a foundation of Soccer match analysis. In this section, we detected and classified some of the most important events using soccer video clips which can be of interest of soccer technical analyzer.
Perspective Transformation
Using this service, you can transform perspective of football video frame into top view which helps coaches and viewers to extract some information (like speed of players or average kilometers each player runs) about performance of players.
Bird's eye view
We can modify this viewing experience from a fully 2D perspective to a near 3D experience that includes a top view and this can be useful for many applications that need player information to evaluate them. We specifically tried to draw a bird's eye view for soccer games.
Keyword Spotting
The primary purpose of developing a Keyword Spotting (KS) system is to detect important football events using the voice of a football reporter. This module helped Imaged and video-based event detection to achieve proper results
Datasets
our datasets for each task which are collected for this project and available as open-source
Contributing
Contributions to this project are welcome, You can also join our team and help us build even more projects like this one
CONTACT USFacts
Our Datasets
Dataset
Image (Event Detection)
Video (Event Detection)
Sound (Keyword Spotting)
Image (Line Detection Dataset)
Image (Segmentation Dataset)
Image (Object Detection Dataset)
Our Datasets
- All
- Segmentation
- Event Detection
- Line Detection
- Bird's eye view
Segmentation 1
Segmentation
Segmentation 2
Segmentation
Segmentation 3
Segmentation
Line Detection 1
Line Detection
Line Detection 2
Line Detection
Line Detection 3
Line Detection
Event Detection 1 (Input)
EVENT DETECTION
Event Detection 1 (Prediction)
EVENT DETECTION
Bird's eye view
Bird's eye view
Team
Each member of our team is a specialist in his or her field
Ali Akhaee
Assistant professor of Electrical Eng
Ramin Toosi
Phd Candidate of Electrical Eng
Alireza Yaghoobpour
MSc Student of MBA in Finance
Iman Masroori
MSc Student of Electrical Eng
Arghavan Aghadavood
MSc Student of Industrial Eng
Amirhossein Kazerooni
BSc Student of Electrical Eng
Mostafa Alavi
BSc Student of Electrical Eng
