I’ve been using Frigate for six months on a raspberry pi 4 with a Google Coral TPU. It’s connected to 2 network cameras streaming in 2mp each.
Frigate standalone works super smooth with no hiccups at all. I am using object detection for people and have not yet had a false positive or false negative. Additionally, I record not only the events, but but also a 24/7 video. Frigate takes care of garbage collecting old assets.
I have it hooked up to my Home Assistant running on the same raspberry pi. From there, I get notifications to my phone which include a live video, snapshot and video recording. The UX and configuration options are way better than any commercial end user product I have found.
It’s been a literal lifesaver, also fun and easy to use. Would recommend 10 of 10. I have no affiliation with the maintainers.
I use Homeassistant and Frigate on a $100 x86 noname micro-machine with five 4K cameras and it is awesome. CPU use does not go above 10%.
Would not claim zero false positives though. However, it is smart enough to filter out non-moving false positives which many cmmercial-grade systems can not, lol.
Can't say it saved my life, but I programmed my smart bulbs to go red if a bear was spotted in any frame in the past 30 min though.
This is hilarious. I programmed my living room to go red if the air quality in my daughter’s room dropped to a certain degree. It should be annoying by now but instead it’s hilarious.
No, my neighbors weed smoke was coming through her closet and raising particulate matter. He’s moved out but we’ve kept the automation and it also cranks up the air purifier.
I did hear about the farting causing VOCs to rise and that kind of happens with us too.
I've also used the same solution, although I ended up scaling from a Pi to a larger 13th gen Intel box with two USB Corals due to number of cameras. It's been ridiculously reliable running from a docker compose stack for years now, including using Watchtower to auto-upgrade the Frigate container. It's really easy to map the corals via docker compose as well.
It's nuts how cheaply you can make such a good system with AI-detection features, its more than paid for itself vs commercial options with monthly fees. High quality weatherproof PoE cameras are crazy affordable now too, and you can VLAN them off your home network with no connection to the internet to further harden the system.
I have almost exactly the same setup, except using the intel gpu for accelerated inference with an OpenVINO Yolo model and HA for notifications. Super reliable.
Bought both back roughly just after Covid era so a while ago. It was even worse during the Covid chip shortage, I had to pay a significant premium over list price for the 2nd one. Haven’t had tried to buy one since so don’t have any advice I’m afraid.
It looks awesome and I look forward to trying it out.
Curious how you claim zero false negatives though (as in missing a person it should have detected), unless you’re reviewing all the data or have another system hooked up to it verifying? Or perhaps you simply mean to imply nothing bad has happened due to a missed detection?
In curious hope it did during Halloween with all the costumes? Are you able to have it pre alert you that kids are coming to the door?
I have set up two zones per camera: The “yard” and the “entry” which is directly in front of the door. Whenever someone is at the entry, I get a notification. Since I walk these paths myself, I have hundreds of test points. Apart from that, I’m happy to _always_ get a notification before the bell rings. And I never have to open the door before I know who is there.
The “yard” part, I review every week. Here, of course, I have no data to compare it to, so I cannot say if it’s missing anything.
So yes, I’m certain it misses nothing that’s important to me - is there someone at my door and who is it.
PS: No Halloween in Switzerland so I cannot tell(;
It works well with other costumes like Trail Running and Hiking gear. It also works in the dark (IR camera) and in crazy hard tests like just peeking around the corner with only part of the face visible.
I've been using it for 2 months now, and I strongly agree - it's very reliable, and object detection is spot on. I'm running 2 cameras with just the cpu, and still have plenty of breathing room.
Sure. The cameras are Tapo C320WS. They are cheap, waterproof, connect to wifi if there’s no ethernet and can stream video in two resolutions at the same time. I use the lower resolution for motion detection and the higher resolution for object detection and event recording.
The whole thing is running in docker-compose on Raspberry Pi and Coral TPU.
Frigate standalone works super smooth with no hiccups at all. I am using object detection for people and have not yet had a false positive or false negative. Additionally, I record not only the events, but but also a 24/7 video. Frigate takes care of garbage collecting old assets.
I have it hooked up to my Home Assistant running on the same raspberry pi. From there, I get notifications to my phone which include a live video, snapshot and video recording. The UX and configuration options are way better than any commercial end user product I have found.
It’s been a literal lifesaver, also fun and easy to use. Would recommend 10 of 10. I have no affiliation with the maintainers.