Show HN: Automatic Baseball Pitching Motion and Trajectory Overlay in Realtime

github.com

28 points·tonychonyy··9 comments

Apologies if this is a noob question, but I wonder how easy it would be to adapt this to other sports, eg cricket. Is the model specific to baseball, or can it be used for any ball-tracking?

Thanks for asking! This is not a noob question.

I would say that the similar workflow could be applied to any ball-related sports. The object detection and the tracking algorithm is basically the same. Then, you could add any sport-specific feature!

For example, I have used a similar method to build AI Basketball Analysis.

https://github.com/chonyy/AI-basketball-analysis

Great point! Looks so much clearer than the early days of HawkEye as well

You may be interested in what Trajekt Sports are building.

https://trajektsports.com/

Thanks, will definitely check it out!

Okay now this is awesome! Great work!

I'm glad that you like it! Thanks a lot!

This looks great! How much data (clips/pitches) did you train your model on?

Thanks for asking! The only model I used in this project is the YOLOv4 object detection model to detect the ball in each frame. I collected about 200 images to train it.

For the other parts like the tracking and the overlay timing, I programmed it by myself.

I implemented SORT algorithm for tracking the ball and some programming logic to capture the overlay timing from each clip.

Reply on news.ycombinator.com