Blue Iris and DeepStack ALPR
- Thread starter MikeLud1
- Start date
I am making good progress on V2.0. Version 1.1 was talking about 2 to 3 seconds to read the plate now with V2.0 it is 1 second
I am getting close to releasing V2.0.
Is anyone using V1.1, if so do you have any issue with it or some suggestions.
Is anyone using V1.1, if so do you have any issue with it or some suggestions.
It should be in the alert folder for the camera that shows the license plate characters
Last night I sent Ken (Blue Iris Support) some changes that will help the DeepStack ALPR integration.
Can you please make some changes the help the integration, they are listed below
Can you please make some changes the help the integration, they are listed below
- When sending Blue Iris a JSON trigger can you have Blue Iris respond with the file name for the alert and add the memo to the log, currently it only shows “external”
- If you turn off Burn label mark-up onto alert images the alert image that is saved is the motion triggered image not the image DeepStack confirmed. Can you please change to the confirmed image
This is freaking cool! I haven't tried it yet (I may have some time this weekend to play around with it), but it looks perfect. I was having many issue swith the ALPR built into BI but I'm looking forward to trying this.
Wait for version 2.0, I should have it posted by end of day Friday
Wait for version 2.0 to fix the issues you are having, I should have it posted by end of day Friday
I plan to. Quick question - we need to input the username/pw of BI in the .ini file. What rights does this userid need (admin, read only, only able to view the camera used for LPR, etc)?
Thanks again! looking forward to trying this!
aesterling
Getting comfortable
@MikeLud1 this is excellent work, as always! Thanks for building and sharing!
A bit of a side question if you don't mind, I'm wondering if I would be able to display the plate characters on screen using BI's overlays, like I'm doing currently with the Plate Recognizer integration?
Example:
A bit of a side question if you don't mind, I'm wondering if I would be able to display the plate characters on screen using BI's overlays, like I'm doing currently with the Plate Recognizer integration?
Example:
I am planning on doing that may not be in version 2.0
Don't worry about looking into it. When I try, I will use an admin account and then work my way down from there after it's working. You're doing enough without worrying about little things like this
I am doing the final debugging on version 2.0. I am going to run some more tests overnight and will release version 2.0 tomorrow. Some of the changes are listed below
- Only one script is needed for V2.0. The script does the cropping and rotation (if needed). Once cropped the script will have DeepStack run the OCR on the cropped plate.
- After the OCR the script will save the DeepStack results in JSON format and YOLO format (for future retraining of the OCR custom model)
- Since there is only one script only one camera is needed with the cropped license plate.
- Also the new version is twice as fast as V1.1 since there is only one script.
looney2ns
IPCT Contributor
