Development of release velocity and spin prediction models for passing machines in American football

Abstract

This article focuses on the development of release velocity and spin prediction models for oval shaped footballs with a state-of-the-art passing machine. Since the trajectory of the ball can be predicted with aerodynamic models, the state of the ball at release time is of interest. At present, no prediction model for this initial state exists. This study measured release spin and velocity. A prediction model was developed based on various ball wear and measured release spin and velocity for different machine configurations. To sensor the motion, a high-speed camera with post image processing was used and release spin and velocity were calculated via regressions. The goal was to predict the release velocity within ±3% in 90% of all relevant cases, depending on the passing machine’s configuration. In addition, the dependency on the wear of the football was investigated. The results show that the release velocity can be predicted, independently of the wear of the ball, with the required accuracy for a reasonable range of machine configurations. For the release spin, a less accurate prediction model was developed. Both prediction models, their limitations and determination are presented in graphical form.

Using Wearable Sensors and a Convolutional Neural Network for Catch Detection in American Football

“…From a sports science perspective, new possibilities open up because of the findings of this paper. A sensor for catch detection, in combination with an automated passing machine such as the one developed in [ 31 ], enables fully automated catch training, which allows for various new training possibilities. For example, an automated passing machine could aim on a designated spot where a receiver should attempt to catch a pass.…”

“… Raw signals (acceleration a in all axis, spin rate around all axis, flux density B in all axis and quantized audio) of the left ( a ) and right ( b ) hand for a caught pass under the circumstances: automated passing machine [ 31 ], standing, facing towards, twohanded, advanced, indoor, Prototype 1. …”

“…Once data is collected with the aforementioned measurement systems, it is processed with specific algorithms starting from simple Butterworth filters to more advanced sensor fusion techniques [ 28 , 29 , 30 ]. Over the last decade, processing the given data with neural networks became more popular [ 11 , 31 , 32 ]. Machine learning provided new analysis methods for data, hence old data could be used to gain new insights [ 10 , 32 , 33 , 34 ].…”

Development and Verification of a Highly Accurate and Precise Passing Machine for American Football

“…Nevertheless, the condition of the initial speed of the football at the time of release was unclear. An experiment [8] found a way to predict the initial speed based on the machine settings.…”

“…The first approach to calculate the extrapolation was to model each of the phases in the passing process. After reviewing the first two phases in the passing process, it was decided to use the model that was developed in [8] to determine the conditions at release time. These conditions served in the free flight phase as initial conditions of the model that described the trajectory.…”