Ken got back to me, and if you have a remote server and auto-start is not set it gets confused and doesn't ping the AI. This will be fixed in the next rollout.
I don't have time today, but does anyone with the same issue who didn't roll back their version of BI enable this feature and run some...
Ok, regarding the issue that I originally posted about here that others seem to be having.....
Ken got back to me, and if you have a remote server and auto-start is not set it gets confused and doesn't ping the AI. This will be fixed in the next rollout.
I don't have time today, but does...
Follow up: I went back to 5.9.8.5 (last version I had a file for) and the plates are working again. Sounds like a BI issue maybe with an external ALPR?
I went back to this, and no dice.....
If I put "license-plate" in there- I am now AT LEAST getting DayPlate/NightPlate. Not ALPR.
I put both in there- just DayPlate. I tried "ALPR" as well in case it was some issue with capitalization on linux v windows.
If I log into my docker container, I see this
root@35475c912a73:/app# ls ./preinstalled-modules/ObjectDetectionYOLOv5Net/custom-models
ipcam-animal.onnx ipcam-combined.onnx ipcam-dark.onnx ipcam-general.onnx license-plate.onnx
root@35475c912a73:/app# ls...
So I had my ALPR working great and reporting to the ALPR database. A couple of days ago-- it just stopped working. I might have updated Blue Iris?
Definitely some of these settings changed since I set it up. I imagine I have something wrong here.
When a car goes by-- I see it finds a car...
About noon the other day my ALPR stopped pinging the AI service.
I think that corresponds to when I updated to 5.9.9.27.
Strangely, I rebooted my CP.AI instance. Rebooted the service.
I get the trigger, but even the AI overlay isn't working.
Strangely, I am getting an object detection...
I was getting this at one point. I have a separate sever for CP. It isn't super powerful.
I found that in cases where these was a lot of movement, sometimes the AI would get inundated with requests from three camera. I just increased the AI timeout from 5 seconds to 15.
I made Zone A the left half of the screen and Zone B is right up against it on the right hand side. Set it to the most sensitive motion and changed from B-C to A-B. No gaps. (one of the videos on line recommended them)
Changed the FPS to 10....
I also looked at my videos and realized now...
Ok- so with about an hours of traffic-- the simple algorithm definitely saw improvement going to 10 FPS.
The zone crossing still missed quite a bit.... This car went by--- totally missed...
So I have an ALPR camera that watches my street and I am happy with the photos it provides. Both day and night. I am also pretty pleased with the ALPR function, and I run codeproject AI on another machine and that runs well.
iframe rate 24. frame rate 24. I shut off substreams for the time...
So can I add "Motion Type" (&TYPE) to the database? And maybe put the confidence in the row as well?
For example, I have a zone B and zone C (left and right respectively). When a car goes by, I have BI report via MQTT.....
Plate detected: 2US673 Probability: 65% MOTION TYPE Motion_B>C...
I did have that set already...
I had something like a 5 second pre-record set in BI and changes it to 2 seconds and it appears to be much better.
I am trying to iron out some issues in BI with regards to detecting the direction of the car. I cloned the camera and just set up a simple motion...
Ok.... I finally put some time into this and got it working. Lots of errors on my end. I was just copying the docker-compose.yml and creating the config, storage and auth directories... I wasn't pulling the whole github with the sql files. So what I ended up doing.
1. Moving to my RH...
mike@ubuntu22:~/Docker/alprDatabase$ docker-compose up -d
ERROR: The Compose file './docker-compose.yml' is invalid because:
'name' does not match any of the regexes: '^x-'
You might be seeing this error because you're using the wrong Compose file version. Either specify a supported version...
Oh man, I don't know how I missed this thread... This looks awesome. I am currently using the LPR data to send via MQTT to Homeseer to control my garage door.
I tried launching the following docker-compose on my Ubuntu machine... (docker-compose 1.29.2)...
I briefly shut off my server and moved my BI to codeproject on my orange pi with the RKNN libraries. Blue Iris did not report any plates. I know the tool work when I show it pictures in the debug screen.....