Page 1 of 1

zmeventserver object detection settings per monitor

Posted: Wed Jan 20, 2021 6:40 pm
by gbruneau
Hello,

I've followed the guide to configure zmeventserver and a standalone mlapi. I would like to only have one monitor use alpr plate_recognizer, monitor with id 8.

I currently have use_sequence=yes set, I also tried it with no but that didn't make a difference. I assume the monitors have to be moved to the ml_sequence or stream_sequence sections but I'm not sure how to define them there. I added the following to objectconfig.ini, but not sure this works with the standalone mlapi. Any thoughts? Thank you!

#Alley
[monitor-8]
detection_sequence=object,alpr
resize=1200

#Front Door
[monitor-4]
detection_sequence=object,face

#Main Door
[monitor-5]
detection_sequence=object,face

#Driveway
[monitor-6]
detection_sequence=object,face

Re: zmeventserver object detection settings per monitor

Posted: Thu Jan 21, 2021 2:29 pm
by asker
I think I'll have to add per monitor support for mlapi. I'll have to review the code - hope to get to it this weekend

Re: zmeventserver object detection settings per monitor

Posted: Thu Jan 21, 2021 2:51 pm
by gbruneau
Thank you, I thought I was missing something.

Re: zmeventserver object detection settings per monitor

Posted: Fri Jan 22, 2021 11:27 am
by asker
As it turns out, this is already enabled.
Edited: See https://zmeventnotification.readthedocs ... -overrides

However, I am going to change this - it's messy this way - monitor specific stuff sits in objectconfig while the rest sits in mlapi. I'll have to think of a better way.