How can we perform segmentation in real-time?

Currently, I think we can only input video via separated frames stored in a directory.
However, for online applications, we should be able to input frames sequentially as they come in.
Are there any existing solutions to facilitate this?
Additionally, are there plans to add such functionality in the future?

Thank you for amazing work!

Start by reviewing the repository's example notebooks and existing video inference flow. Determine whether sequential frame input is supported, and document or scope what would be required for real-time segmentation and what a complete solution would demonstrate.

Written by the indexing model from the issue text.