I've got something similar to this using cheap ONVIF security cameras and kasa smart bulbs. I have an nvidia card process the capture and for the smart speaker I use just a microphone and speaker hooked up to a normal computer. The architecture is spread across many machines and it's nowhere close to this realtime. Also the video capture is fairly lousy because the lighting and resolution and coverage isn't great. The cameras can change the lighting to try to get a better shot. (well it's qwen with toolcalls)
I also have (I think, haven't counted recently) 12 cameras that are all ballhead so they move around and look for me when I say something to the smart speaker.
But I didn't think of the projector ... there's ~$30 ones ... might be worth buying a few.
Getting this level of response, feedback and accuracy, that's the real magic. The latency is garbage. I'm just using cheap OTS hardware though.
Anyone can do this ... it's not that expensive. Smart bulbs are cheap, wifi cams are cheap, omnidirectional usb microphones are cheap and projectors are cheap too. I'm talking like ~$100 total
still researching them ... some of these look like garbage ... i'll come back to this thread in a few days when i find something decent. I don't want high nits or resolution, just want to be able to send pixels and not have it be noisy and get a response in under 500ms.
I also have (I think, haven't counted recently) 12 cameras that are all ballhead so they move around and look for me when I say something to the smart speaker.
But I didn't think of the projector ... there's ~$30 ones ... might be worth buying a few.
Getting this level of response, feedback and accuracy, that's the real magic. The latency is garbage. I'm just using cheap OTS hardware though.
Anyone can do this ... it's not that expensive. Smart bulbs are cheap, wifi cams are cheap, omnidirectional usb microphones are cheap and projectors are cheap too. I'm talking like ~$100 total