New CodeProject.AI Object Detection (YOLO11 .NET) Module

slickcam said:
My mistake, I mistook your original comment thinking you are talking about number of lines; now I see, you are talking about multiple objects in the same line. Yes, other additional car or trucks are stationary, meaning, those are present in the path (parked) when new car or truck comes by. Then CPAI detects those and makes multiple entries in that one line. I don't know how to make CPAI to only report the new one that is arriving and to ignore the ones already stationed or parked.
Click to expand...
Ah that's a whole other thing about Periodic AI Inspection ignore stationary objects etc. etc.

I don't know if setting that up will lower your detection time though, I was (falsely) operating under the assumption it was only supposed to be finding one thing and the multiple items were it finding the same thing using multiple models.

Ignore me!
 
ipcamwalt said:
Ah that's a whole other thing about Periodic AI Inspection ignore stationary objects etc. etc.

I don't know if setting that up will lower your detection time though, I was (falsely) operating under the assumption it was only supposed to be finding one thing and the multiple items were it finding the same thing using multiple models.

Ignore me!
Click to expand...
No worries, I learnt something in the process of responding to you. Now, I am going to dig further on that AI tab to see how I can make it better for my use case.
 
slickcam said:
Hi Mike, Any thoughts on the screenshot I shared, just wondering if there is anything I can do to make it better. Thanks for all your help.
Click to expand...
I wanted to see if the module is using your GPU and not the CPU which it is. One thing you can check make sure you are not sending main stream for object detection, it does not improve accuracy, it only slows down the detection.
 
  • Like
Reactions: Flintstone61
MikeLud1 said:
I wanted to see if the module is using your GPU and not the CPU which it is. One thing you can check make sure you are not sending main stream for object detection, it does not improve accuracy, it only slows down the detection.
Click to expand...
Thank you. I’m currently using the sub-stream for AI detection because sending the main stream results in an average latency of over 325 ms.
I have one off-topic question: I’m using the audio-intensity trigger in Blue Iris to record when the sound level exceeds a certain threshold, mainly to capture my dog’s barking. However, it triggers on any loud sound.
Is there a way to use CPAI so that Blue Iris alerts only when the sound is specifically a dog bark? In other words, can BI + CPAI be used for dog-bark detection?
 
You must log in or register to reply here.
Top Bottom