본문 바로가기
  • Home

Tennis Player Tracking and Distance Measurement Using DeepSORT and Homography

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2025, 30(11), pp.125~131
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : September 10, 2025
  • Accepted : October 22, 2025
  • Published : November 28, 2025

Hyun-Il Kim 1 Seung-Bo Park 1

1인하대학교

Accredited

ABSTRACT

High-cost modern sports analysis systems are predominantly utilized by elite athletes, creating a significant technology gap that limits access for amateur players and sports enthusiasts. To address this issue, this study proposes a practical method for measuring the movement distance of tennis players using only a single, commonly available camera. Our approach combines YOLOv8n and DeepSORT for robust player detection and tracking, followed by a homography transformation based on court keypoints to map 2D image coordinates to real-world metric coordinates. A Kalman filter is then applied to smooth the resulting trajectory and derive a reliable metric of movement distance. When tested on real tennis match footage, the proposed system achieved an average measurement accuracy of 85.26% relative to manual analysis tools, demonstrating its viability as a low-cost alternative.

Citation status

* References for papers published after 2024 are currently being built.

This paper was written with support from the National Research Foundation of Korea.