I just want to ask if it’s possible to create a video call with object detection on it, So the idea is to create a web-based video call application (like google meet or zoom) where users can join a room and the user can open their camera and microphone, when they open their camera that’s when the object detection happen, the application will take logs on if it detected something like a person or if a person is holding a phone or any devices and only the instructor or admin can see the logs.
My idea is to use OpenCV like this to performed object detection, I plan to create this in python with Django or flask, and I am plan implement the object detection model using a YOLO algorithm with Porch and OpenCV. but I am not sure if this is possible, I try to search and find something similar but couldn’t find one so If you have any ideas on how can I achieve this or any advised that you can give to me something like a roadmap to build the application or if you know some similar project, any help will be appreciated.

