1. build a yolo based cat detector to detect where yuri is
2. then build an action recognition on video (there are many good action recognition approaches such as videoMAE etc that could be leveraged to detect normal cat activity vs abnormal
activity.
Video recognition may be tough. My dog has epilepsy and some of his seizures are basically him laying very stiffly on the ground for 3 to 6 minutes with relatively minimal shaking. Yuri's seizures may be much more pronounced (I didn't watch the video...), but I'd wager physical measures will be less failure prone. Though both together may provide the best coverage.
> Yuri's seizures may be much more pronounced (I didn't watch the video...)
The seizures in the video are very pronounced, you can’t miss them. But that’s not Yuri, it’s a different cat named Charlie. Though from the OP’s description, their cat may be similar.
They are similar, yes, but they might happen if he's under a table or a bed which makes video tracking really difficult. Someone suggested using a bodycam and that might be an interesting solution, if I can find one that streams video instead of just storing it in an SD card.
1. build a yolo based cat detector to detect where yuri is
2. then build an action recognition on video (there are many good action recognition approaches such as videoMAE etc that could be leveraged to detect normal cat activity vs abnormal activity.
hope that helps.