FootAndBall: Integrated player and ball detector

TL;DR

FootAndBall is a specialized, efficient deep neural network for real-time detection of players and the ball in high-resolution soccer videos, utilizing a feature pyramid architecture for improved small object detection.

Contribution

The paper introduces a novel, lightweight neural network architecture tailored for soccer video analysis, enabling real-time detection with significantly fewer parameters than generic detectors.

Findings

Achieves real-time processing of high-resolution videos.

Uses a feature pyramid network to improve small object detection.

Has two orders of magnitude fewer parameters than standard detectors.

Abstract

The paper describes a deep neural network-based detector dedicated for ball and players detection in high resolution, long shot, video recordings of soccer matches. The detector, dubbed FootAndBall, has an efficient fully convolutional architecture and can operate on input video stream with an arbitrary resolution. It produces ball confidence map encoding the position of the detected ball, player confidence map and player bounding boxes tensor encoding players' positions and bounding boxes. The network uses Feature Pyramid Network desing pattern, where lower level features with higher spatial resolution are combined with higher level features with bigger receptive field. This improves discriminability of small objects (the ball) as larger visual context around the object of interest is taken into account for the classification. Due to its specialized design, the network has two orders of magnitude less parameters than a generic deep neural network-based object detector, such as SSD or YOLO. This allows real-time processing of high resolution input video stream. Our code and pre-trained model can be found on the project website: https://github.com/jac99/FootAndBall .