Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

multizone, different detection_sequence #334

Closed
Scoobler opened this issue Oct 28, 2020 · 1 comment
Closed

multizone, different detection_sequence #334

Scoobler opened this issue Oct 28, 2020 · 1 comment

Comments

@Scoobler
Copy link

Scoobler commented Oct 28, 2020

Event Server version

6.0.5

Hooks version (if you are using Object Detection)

0.1.3

The version of ZoneMinder you are using:

1.34.22

What is the nature of your issue

Enhancement

Details

I am currently using the ***_zone_detection_pattern using the ZM defined zones - I want to be able to match every object and every face in any zone - however I only want to add ALPR recognition in a specific zone.

One zone I have covers the driveway, if there is a vehicle there I want to detect registration, however another zone captures the road. I would like object detection to take place so each recording is tagged when sifting through footage, however registrations become less important as the registrations are not on a visible angle, so it is firing off to the cloud and consuming the daily limit of checks.

Along with I think issue #101 it would be perfect, as I really only want a notification for detections on the driveway, however I also want all objects in other areas to be logged, just not notified.
I hope that makes sense and I am not missing something that will already do this?

Thanks!

@pliablepixels
Copy link
Member

I understand the ask, but not something I plan to do. The way detection is wired today is that it first detects and then does a zone intersection check later. This is because detection happens at an image level, and an image can contain multiple zones. To do what you want, I will have to split an image into zone segments and then run analysis on each one. That won't work for the following reasons:

  • objects that partially intersect with zones will fail to be detected
  • slows down the entire system (running detection 5 times for 5 zones in an image, instead of one)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants