# AI Driven Soccer Analysis Using Computer Vision

Source: [AI Driven Soccer Analysis Using Computer Vision](<https://www.sota2.com/research/paper/69dc78917d0172140ec78b27>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-14T05:00:04.234Z

Authors: Adrian Manchado, Tanner Cellio, Jonathan Keane, Yiyang Wang

Published: 2026-04-09T19:19:40.000Z

## Abstract

Sport analysis is crucial for team performance since it provides actionable data that can inform coaching decisions, improve player performance, and enhance team strategies. To analyze more complex features from game footage, a computer vision model can be used to identify and track key entities from the field. We propose the use of an object detection and tracking system to predict player positioning throughout the game. To translate this to positioning in relation to the field dimensions, we use a point prediction model to identify key points on the field and combine these with known field dimensions to extract actual distances. For the player-identification model, object detection models like YOLO and Faster R-CNN are evaluated on the accuracy of our custom video footage using multiple different evaluation metrics. The goal is to identify the best model for object identification to obtain the most accurate results when paired with SAM2 (Segment Anything Model 2) for segmentation and tracking. For the key point detection model, we use a CNN model to find consistent locations in the soccer field. Through homography, the positions of points and objects in the camera perspective will be transformed to a real-ground perspective. The segmented player masks from SAM2 are transformed from camera perspective to real-world field coordinates through homography, regardless of camera angle or movement. The transformed real-world coordinates can be used to calculate valuable tactical insights including player speed, distance covered, positioning heatmaps, and more complex team statistics, providing coaches and players with actionable performance data previously unavailable from standard video analysis.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Keypoint Prediction on Field Keypoint Dataset (train)](<https://www.sota2.com/research/sota/keypoint-prediction-on-field-keypoint-dataset-train.md>): Keypoint Prediction; Field Keypoint Dataset (train); Accuracy: 99.89.

- [Keypoint Prediction on Field Keypoint Dataset (test)](<https://www.sota2.com/research/sota/keypoint-prediction-on-field-keypoint-dataset-test.md>): Keypoint Prediction; Field Keypoint Dataset (test); Accuracy: 97.18.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.08722>)

[PDF](<https://arxiv.org/pdf/2604.08722.pdf>)
