AugusteCouecou

Do you have an example of object tracker working in standalone ? Because this example given in the Stanalone doc is actually using CV2 luxonis/depthai-experimentstree/master/gen2-people-tracker

Thank you very much for these informations !

Hello dear Oak cameras experts, I have an issue running this code in standalone mode, the code work well when launch with the computer but I don't have anything in my catchbox when I run it from the camera itself

Model of camera : OAK-1 POE
Model of detection : yolo_V10 (put in .blob extension at the root of the file)
python version. : 3.9

depthai :2.28

Bootloader : 0.0.28

I think the issue could be related to the libraries I am using (cv2 for example) but I am not sure of it

the code :

https://docs.google.com/document/d/1bFVA7avRCgw2RDAA3uZfZqGGB-hW-5wE8rx-wPjrOR8/edit?usp=sharing

If someone can give me a hint on what is wrong with the code I would really appreciate it

thanks by advance

Hello

I have a OAK-1 POE camera and my goal is to track people in an area so the resolution is pretty important.

I am pretty new to the world of Detection model embedded in a camera but I would like to know why when I run the depthAI viewer I have yoloV8 running perfectly smooth in the native resolution of the camera (1920x1080) and when I use the python sdk I can only use the 416x416 resolution and the yolo models seems to be trained at a max fixed resolution of 640x640.

If you have any pointers it would help me a lot

Thanks by advance