hbr VS AI-basketball-analysis

I wrote hbr (handbrake runner) [0]. It takes a global config, a per-file config, and individual outfile sections then calls HandBrakeCLI to encode video. I use it to encode movies/series from optical media.

Additionally there is hbscan.py to generate a list of potential outfiles from handbrake's --scan argument. One day I'd like to integrate it with hbr (in C) using peg/leg [1]. Currently using pyparsing.

This is still a lot of manual work, but it saves doing it twice. When you find a mistake in an encode there's a log with the file, and it's easy to go back and modify the keyfile and re-encode it.

[0] https://github.com/epakai/hbr

[1] https://www.piumarta.com/software/peg/ (not mine)

I wrote handbrake runner. It takes a plaintext (glib) keyfile and runs HandBrakeCLI repeatedly to encode video. I use it for my dvd/bd collection. It has a support script (hbscan.py) to build keyfile templates from handbrake's scan of dvd titles.

https://github.com/epakai/hbr

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

I built an app to visualize and analyze basketball shots and shooting pose with machine learning.

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

The result is pretty nice. However, the only problem is the slow inference speed. I'm now refactoring the project structure and changing the model to a much faster YOLO model.

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