AXIS Q1798-LE Crowd counting APP for back end?

[Chimpwaite]

Hello,

I was wondering if there was a crowd counting app available for the AXIS Q1798-LE (Static Bullet camera).

I cannot seem to find one, and on the Axis website they have the crowd counting app but this camera does not show in the list of compatible models.

I am not interested in the computer/server doing the counting, I want the camera itself to take the grunt of it.

Any help would be greatly appreciated, thanks.

Regards

Dan

[github-actions[bot]]

This automatically generated reply acts as a friendly reminder.

Answers to your questions will most often come from the community, from developers like yourself. You will, from time to time, find that Axis employees answers some of the questions, but this is not a guarantee. Think of the discussion forum as a complement to other support channels, not a replacement to any of them.

If your question remains unanswered for a period of time, please revisit it to see whether it can be improved by following the guidelines listed in Axis support guidelines.

[whittenator]

Hello,

I was wondering if there was a crowd counting app available for the AXIS Q1798-LE (Static Bullet camera).

I cannot seem to find one, and on the Axis website they have the crowd counting app but this camera does not show in the list of compatible models.

I am not interested in the computer/server doing the counting, I want the camera itself to take the grunt of it.

Any help would be greatly appreciated, thanks.

Regards

Dan

Not a plugin/app to my knowledge. However, you could create your own crowd counting app using an Object Detection model through the Native SDK or the Computer Vision SDK(https://github.com/AxisCommunications/acap-computer-vision-sdk-examples). Looks like your particular camera model uses the armvh7f and can thus be used with the Computer Vision SDK.

To quickly get this done, follow this C++ example or this Python example.
The default models they have in the Docker.model file will actually detect the "person" class pretty well. You can simply create a counter for every person that has been detected.(You can have it overlay on the image itself or you can send it off somewhere else for analysis or storage).