Precise 3D Baseball Pitching Trajectory Estimation Using Multiple Unsynchronized Cameras

Joongsik Kim,Moonsoo Ra,Whoi-Yul Kim,Hongjun Lee,Jeyeon Kim

doi:10.1109/access.2019.2953340

Joongsik Kim, Moonsoo Ra + Show 3 more

Open Access

https://doi.org/10.1109/access.2019.2953340

Copy DOI

Abstract

We developed a method for the precise estimation of the 3D trajectory of a baseball by modeling the movement of the baseball and estimating the capture delay, using multiple unsynchronized cameras. To develop the proposed algorithm, we mimicked the real-world process of capturing a baseball in simulation space, and analyzed the capture process using a multiple unsynchronized camera system. We represented the movement of the baseball using a piece-wise spline model, and predicted the position of the baseball in the subframes in a manner which is robust to position error and change in direction of movement of the baseball. This method accurately predicts the baseball position over time by modeling the movement of the baseball in a real baseball game environment, and improves the accuracy of the reconstructed 3D baseball trajectories. We defined an objective function to estimate the capture delay, and estimate the optimal capture delay parameter using non-linear optimization method. In addition, we evaluated the performance of the proposed method in simulation space and in a real-world situation. The experimental results show that the proposed method can estimate a 3D baseball trajectory precisely using a multiple unsynchronized camera system and is robust to variations in capture delay, both in the simulation space and in real-world situations.

Highlights

In recent years a number of different baseball pitching analysis systems have been used to help viewers and players better understand the game
Many broadcasters and baseball clubs have adopted the use of trajectory analysis systems, and trajectory information output from these systems can be used as content for baseball broadcasts, VR baseball game data, and pitching training information
We have developed a 3D trajectory reconstruction method involving modeling the motion of a baseball using piece-wise spline function and optimizing the optimal capture delay parameters in a multiple unsynchronized camera system

Summary

Introduction

In recent years a number of different baseball pitching analysis systems have been used to help viewers and players better understand the game. Many broadcasters and baseball clubs have adopted the use of trajectory analysis systems, and trajectory information output from these systems can be used as content for baseball broadcasts, VR baseball game data, and pitching training information. A trajectory analysis system uses different types of image capture devices to detect a baseball. Initial systems highlighted the baseball’s location and showed its position on the broadcast screen [2]. This type of system only shows discrete ball locations from a specific viewing angle, and cannot obtain other data such as spin, velocity or 3D location.

Objectives

Results

Conclusion