Question - BI and CPAI detects Person but still goes to Cancelled Alerts

mvoss

Getting the hang of it
Oct 21, 2023
72
66
Texas
Hello,

I'm trying to figure out why this was thrown into my cancelled Alerts when CPAI detects the perosn. Any thoughts or ideas would be appreciated.
This doesn't happen all the time on this cam but every once in a while.

Thanks,
Michael
 

Attachments

  • AI Screen.png
    AI Screen.png
    221.4 KB · Views: 43
  • Alerts.png
    Alerts.png
    415.9 KB · Views: 41
  • Motion Screen.png
    Motion Screen.png
    266.1 KB · Views: 36
1 observation: Your 2nd screenshot doesn't match your 1st screenshot. Are both screenshots from same cam?

In your 2nd screenshot, at the top, I see "Person" for confirm. That is DIFFERENT than "person" detected with ipcam-combined model (further down.)

If it's not clear, it can be case sensitive. So if you intend to use ipcam-combined model, make sure to specify "person" --- all lower case in your AI config.
 
1 observation: Your 2nd screenshot doesn't match your 1st screenshot. Are both screenshots from same cam?

In your 2nd screenshot, at the top, I see "Person" for confirm. That is DIFFERENT than "person" detected with ipcam-combined model (further down.)

If it's not clear, it can be case sensitive. So if you intend to use ipcam-combined model, make sure to specify "person" --- all lower case in your AI config.
[/QUOTE

I did change the "case" of the alerts this morning to see if that would matter, after this alert was cancelled. Maybe that is why they are different?
 
under the to cancel line try putting "giraffe" without the quotes. This will force CPAI to run a full analysis on all of the images until it finds something in the to confirm line. And only then will it cancel the alert if nothing is found.
 
@kaltertod Your advice is a possible option but I would use it judiciously. Why? the downside is that an alert will only trigger after 10 images have been processed---each time (for the above OP config). And if you look at the CP.AI processing time for each image (not very performant), there could be a measurable delay before you get alerted.

My preference is no false alerts with short delay so I usually configure AI for 4-5 images at 80-85% confidence, cancel box is empty, with Nvidia GPU for fast CP.AI timesScreenshot 2024-01-05 at 2.13.09 PM.png
 
Last edited:
  • Like
Reactions: mvoss
I would rather have a clear picture of what is going on vs a picture of a persons arm.... The performance is very hardware dependent I analyze up to 900 images per trigger with a high accuracy 90%+ applied to get the clearest image in the alert. My servers only take 1-2 seconds to fire off the alert after the initial alert is sent to CPAI. To me that is fast enough as I cannot dial the police or get to my door that fast. But the alert time is not so important on my config vs positive identification of the subject material. I also record all streams 24/7 in case something gets missed.

In the case of the op 250ms per image at 10 images would only be 2.5 seconds for positive identification. It takes longer for the alert to be sent than the delay in analyzing it depending on the network/internet speed. The main thing I was going off of was the op's want to know why the "person" detected ended up in the canceled alerts, adding giraffe to the To Cancel line would help alleviate that, giving the AI more time to finish analyzing the images given to promote an active alert vs a canceled one.

My suggestion to the op would be to increase the amount of images analyzed slightly, reduce the analyze time to fire at 250ms, along with increase the accuracy quite a ways. If he/she is still getting canceled alerts I would add giraffe to the to cancel line.

The bottom line is there is always give and take on a case by case basis, Because every use case is situational. All we can do is make suggestions to help them along ;)
 
  • Like
Reactions: mvoss
so i have BI up and running. can anyone tell me where the trigger on code project setting is? I have a paid license.


1704743720550.png