Our work allowed us to select a PC or Mac or Linux workstation maybe 15 years ago. I had a Redhat station to do actual work and Windows box to edit documents and email. About 10 years ago, one guy went Mac and we all followed suit. It integrates SO much better with Linux workstations out of...
I am using Codeproject.ai on an old Xeon E3 and my CPU times are about equivalent to yours. About 500-600 ms for a plate.
I use my ALPR data to open the garage doors, so latency is somewhat of an issue. I think I analyze like 30 frames everytime a car drives by. I am hoping to get that...
Been thinking about building a new machine to run everything rather than the 3-4 machines I have now. I have Codeproject.ai working in Docker and pass through the coral.ai but that doesn't help with ALPR. I have been thinking of getting a NVIDA card to accelerate ALPR and object detection. I...
I was having perhaps some high CPU with Codeproject.AI after a few days. Last week I set a crontab to restart the container at 3 AM. I didn't watch the memory usage.
Interesting....
I am running BI on an old E3-1245 because it has Quicksync. I am using substreams but kept the hardware acceleration. I have not noticed any instability since I moved the OS to a SSD.
I have another server running an old E3 without Quicksync. That runs Homeseer/HomeAssistant...
I recently installed a Coral.AI and got the drivers working in my server. It works really well but I am getting the following error that someone else got. I set the model to be medium and that does NOT work for me. Any other setttings I should try...
I moved my Google dual TPU to my Rocky Linux 9 machine. I see the TPUs just fine with lspci.
[mike@nas src]$ lspci|grep TPU
08:00.0 System peripheral: Global Unichip Corp. Coral Edge TPU
09:00.0 System peripheral: Global Unichip Corp. Coral Edge TPU
I installed the COPR driver for Fedora from...
The other option is to put an active POE switch (that runs off of POE) near the camera. I have several Ubiquity 5 port Flex switches on our properties.
I have a camera that the spiders love to build near and I get a lot of false motion sensors. I was noticing this is hitting my AI server a lot-- so I shut off AI alert for the time being and I still see Codeproject AI ping the camera on motion. Version 9.9.33....
Any ideas?
Very true... but the Xeon runs my NAS 24/7. Incremental cost is negligible. I think I am the once who convinced Mike Lud to use the RKNN libs. I probably should use it.
According to this... Massachusetts and California has the same average price for electricity. I am a good candidate for...
I have an Orange Pi and I am not sure I get much better results than my Xeon E3 which is probably 10 years old at this point. Agree-- bump that timeout to 60.
I loved the new Model Y. I am going to pick one up when my car finally gives up the ghost. Maybe I will throw a gun rack in the back to keep keyers away.
Yeah, I use a CPU and it is fine for the database. If you analyze 30 frames at 500 ms per frame (worse case), it takes 15 seconds. Unless you are on a busy street who cares.
I use a CPU for detection. It takes me maybe 1/4 to 1/2 a second to read a plate. If I analyze 30 images whenever a plate comes by, it take worse case 15 seconds of CPU time. My street is pretty slow.. Maybe 25 houses on it. If you just want to add it to a database and not make any quick...
If you cloned the camera-- and one "camera" was on the left-- and one was on the right, I wonder if you would have more success...
Bascially, have a Zone A on each which is just the side of the camera.
I complete agree with Mike here. You are masking out your image by not having a full zone.
Couple other things...
1. You are triggering A>B. You will only get cars going left to right in your image. If you want both, try A-B. You might even not want to do zone crossing at all to catch...
Are you running in Docker? I had to specify my Timezone in the docker-compose.yml file. It reverts to GMT.
environment:
- NODE_ENV=production
- ADMIN_PASSWORD= # Change this to a secure password
- DB_PASSWORD= # Change this to match your postgres password
-...
The web server 500 error-- I got that one. It was due to me putting the wrong JSON in on the Blue Iris side. This is what I have now.
{"ai_dump":&JSON, "Image":"&ALERT_JPEG", "camera":"&CAM", "timestamp":"&ALERT_TIME" }