A system is disclosed that includes a ball-throwing machine included within a first housing, a controller communicatively coupled to the ball-throwing machine and included within a second housing different than the first housing, a camera, and a non-transitory storage medium having stored thereon logic, the logic being executable by one or more processors to perform operations including: receiving information associated with a selection of a first training drill from the controller, responsive to receiving the information associated with the selection of the first training drill, causing the ball-throwing machine to impart motion to one or more balls in accordance with the first training drill, receiving multimedia data of a player captured by the camera, and performing a player recognition procedure to locate the player within the multimedia data.