out=Parse(obs1,obs2)

[boyGitHu]

Hello, I have a question for you. Generally speaking, you only need one video frame as a whole as input to the program, but I see that in the fish_tracking.py program, the front and back frames are divided into two parts for differencing, and then the last one is processed again with your own Parse method, why is it divided into two parts for differencing and what is the purpose of the Parse method?

[boyGitHu]

And is it convenient to provide the original input video？