I’ve been following a YouTube tutorial on calculating time in different zones using computer vision. The tutorial demonstrates the process using streaming videos, but I want to adapt it to work with recorded videos in Google Colab.
**Here’s the link to the video:
Has anyone here tried something similar or could offer some guidance on how to get started? Any tips or code snippets would be greatly appreciated!
Were you talking about this video? If so, a good tutorial that does something like that (also using a polygon feature!) is this cookbook by Leo.
It uses the sink function to:
break all the images into their own specific frames
annotate on each frame
add all the annotated frames back into one video!
Let me know if you need any other advice as I created a project that utilized prerecorded audio too! Happy to help with your project anytime