Soccer Player Tracking in Low Quality Video

TL;DR

This paper presents a system for tracking multiple soccer players effectively in low-quality videos by adapting existing tracking methods and creating new datasets for different video qualities.

Contribution

The paper introduces a novel adaptation of multiple object tracking for low-quality soccer videos and provides new datasets for various video qualities.

Findings

High performance in low-quality video tracking

Effective adaptation of state-of-the-art tracking methods

Creation of new datasets for different video qualities

Abstract

In this paper we propose a system capable of tracking multiple soccer players in different types of video quality. The main goal, in contrast to most state-of-art soccer player tracking systems, is the ability of execute effectively tracking in videos of low-quality. We adapted a state-of-art Multiple Object Tracking to the task. In order to do that adaptation, we created a Detection and a Tracking Dataset for 3 different qualities of video. The results of our system are conclusive of its high performance.