Skip navigation
  • 中文
  • English

DSpace CRIS

  • DSpace logo
  • Home
  • Research Outputs
  • Researchers
  • Organizations
  • Projects
  • Explore by
    • Research Outputs
    • Researchers
    • Organizations
    • Projects
  • Communities & Collections
  • SDGs
  • Sign in
  • 中文
  • English
  1. National Taiwan Ocean University Research Hub
  2. 工學院
  3. 機械與機電工程學系
Please use this identifier to cite or link to this item: http://scholars.ntou.edu.tw/handle/123456789/21995
Title: Magnus-Forces Analysis of Pitched-Baseball Trajectories Using YOLOv3-Tiny Deep Learning Algorithm
Authors: Wen, Bor-Jiunn 
Chang, Che-Rui
Lan, Chun-Wei
Zheng, Yi-Chen
Keywords: magnus force;pitched-baseball trajectory;YOLOv3-tiny deep learning algorithm;ball speed;spin rate
Issue Date: 1-Jun-2022
Publisher: MDPI
Journal Volume: 12
Journal Issue: 11
Source: APPLIED SCIENCES-BASEL
Abstract: 
This study analyzed the characteristics of pitched baseballs from TV broadcast videos to understand the effects of the Magnus force on a pitched-baseball trajectory using aerodynamic theory. Furthermore, an automatic measurement and analysis system for pitched-baseball trajectories, ball speeds, and spin rates was established, capturing the trajectory of the baseball thrown by the pitcher before the catcher catches it and analyzing its related dynamic parameters. The system consists of two parts: (1) capturing and detecting the pitched baseball in all frames of the video using the YOLOv3-tiny deep learning algorithm and automatically recording the coordinates of each detected baseball position; (2) automatically calculating the average speed and spin rate of the pitched baseball using aerodynamic theory. As the baseball thrown by the pitcher is fast, and live-action TV videos like sports and concerts are typically at least 24 fps or more, this study used YOLOv3-tiny algorithm to speed up the calculation. Finally, the system automatically presented pitching data on the screen, and the pitching information in the baseball game was easily obtained and recorded for further discussion. The system was tested using 30 videos of pitched baseballs and could effectively capture the baseball trajectories, throw points, catch points, and vertical displacements. Compared with the values from the TV broadcast, the average errors on the calculated ball speed and spin rate were 1.88% and 7.51%, respectively. Using the ratio of the spin rate and ball speed as a parameter to analyze the pitching state of the pitcher's four-seam fastball in the Nippon Professional Baseball and Major League Baseball matches, it was observed that when this ratio increased, the Magnus displacement of the ball increased, thereby decreasing its late break. Therefore, the developed system provides scientific pitching data to improve the performance of baseball pitchers.
URI: http://scholars.ntou.edu.tw/handle/123456789/21995
DOI: 10.3390/app12115540
Appears in Collections:機械與機電工程學系

Show full item record

WEB OF SCIENCETM
Citations

3
Last Week
0
Last month
0
checked on Jun 27, 2023

Page view(s)

182
Last Week
0
Last month
checked on Jun 30, 2025

Google ScholarTM

Check

Altmetric

Altmetric

Related Items in TAIR


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Explore by
  • Communities & Collections
  • Research Outputs
  • Researchers
  • Organizations
  • Projects
Build with DSpace-CRIS - Extension maintained and optimized by Logo 4SCIENCE Feedback