Combined object detection and pose estimation. Possible on an Axis ARTPEC-8 ?

[MarcoHess]

I am new to Axis cameras and currently considering using an M4317-P panoramic view camera mounted on a wall (as opposed to a ceiling). In a previous job I developed na embedded camera for detecting different wildlife so I know a little bit about how YOLO works.

For my current application I need a combination of object detection and pose detection. i.e. the objects detection needs to detect persons and typical items such person can have when travelling like a bag, backpack, travel roller bag, etc. and then for the person I need to detect their pose so I can see where they stand and face the right way.

I am hoping to do all that on the edge in the camera. I am reading up on the ACAP platform and there are various examples for object and pose detection and also there is a YOLOv5 example. I have noted from some web research that both YOLOv5 and SSD have examples of pose detection. I also recall having seen an example of a combined model in which the inference output showed both the object and the pose but can't find it anymore.

Have people seen or used combined object detection and pose estimation from the same model?

Is it realistic to run this in ARTPEC-8 device?

[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.

[Corallo]

Hello @MarcoHess
Do you perhaps refer to this?
https://github.com/TexasInstruments/edgeai-yolov5/tree/yolo-pose