MikeLud1
IPCT Contributor
Is this the full image that you are trying to ALPR, it needs to be like the below image
Blue Iris and CodeProject.AI ALPR
- Thread starter MikeLud1
- Start date
The plate needs to be bigger.
Ideally the field of view should be not much bigger than the vehicle as shown in the example above that @MikeLud1 posted.
Keep in mind that this is a camera dedicated to plates and not an overview camera also. It is as much an art as it is a science. You will need two cameras. For LPR we need to OPTICALLY zoom in tight to make the plate as large as possible. For most of us, all you see is the not much more than a vehicle in the entire frame. Now maybe in the right location during the day it might be able to see some other things, but not at night.
Ideally the field of view should be not much bigger than the vehicle as shown in the example above that @MikeLud1 posted.
Keep in mind that this is a camera dedicated to plates and not an overview camera also. It is as much an art as it is a science. You will need two cameras. For LPR we need to OPTICALLY zoom in tight to make the plate as large as possible. For most of us, all you see is the not much more than a vehicle in the entire frame. Now maybe in the right location during the day it might be able to see some other things, but not at night.
That is correct! Get a varifocal that you can optically zoom it to the size of the vehicle.Ah makes sense, so I should put a camera at the entrance pointing to where the number plate would be.
Ill get that donethanks!
What Database is this that you are searching?
hopalong
Getting the hang of it
MikeLud1
IPCT Contributor
I am still trying to figure out the best way to improve the ALPR module. If you can send me some samples of the night images that has issue.
hopalong
Getting the hang of it
PM sent with some recent images that got missed.
I installed CUDA 11.7 and it is working as expected. Thanks.
wpiman
Pulling my weight
Any chance this could be added to the arm64 versions of Codeproject? I am playing around with a Orange Pi 5 which is is maybe 80% faster than a RPI 4. I am trying to compare that to my old Xeon server running windows.
I also might run this on an M1 Mac which can run ARM docker files... That processor appears to really haul ass..
That said, all my benchmarking shows the oldschool xeon E3s running codeproject.ai on windows as being the fastest still?
MikeLud1
IPCT Contributor
There is a Docker arm64 version of CodeProject.AI see the below link. I have not tried the arm64 , let me know if it works for you.
Running CodeProject.AI Server in Docker - CodeProject.AI Server v2.2.4
A Guide to using and developing with CodeProject.AI Server
www.codeproject.com
wpiman
Pulling my weight
Sorry, should have been more clear. I got the ARM64 project working no problem, but it says the ALPR is not available...There is a Docker arm64 version of CodeProject.AI see the below link. I have not tried the arm64 , let me know if it works for you.
Running CodeProject.AI Server in Docker - CodeProject.AI Server v2.2.4
A Guide to using and developing with CodeProject.AI Server
MikeLud1
IPCT Contributor
MikeLud1
IPCT Contributor
The best is CodeProject.AI Windows version.
OK, question. I am trying CodeProject again. In Docker Desktop are you supposed to run platerecognizer/alpr under images for CodeProject?
Keeo getting an error "AI not responding. When I go to check it under codeproject explorer and check an image it times out every time and gives the following message "The request timed out (#reqid {request.reqid})". Also CodeProject keep going offline.
Rick
Last edited:
wpiman
Pulling my weight
Thank you. I see that it worked under macos-arm64. I tried that as well..
The docker image doesn't have a "macos-arm64" tag so I just used arm.... I might have to open up the container a bit and see if I can set the plaform in the modulesett0ngs.platform json file.
The docker image doesn't have a "macos-arm64" tag so I just used arm.... I might have to open up the container a bit and see if I can set the plaform in the modulesett0ngs.platform json file.