AACS VS dlstreamer

You could do this with Android auto (over USB). This could help you https://github.com/tomasz-grobelny/AACS, but an arduino can't handle it. This will get complicated.

So I have been looking at a way to make a headless KWin Wayland that writes to a socket in the BGRA raw format. This is for an android auto server https://github.com/tomasz-grobelny/AACS also how do I send touch screen input. Thanks for reading.

I dunno if this is the proper place to ask about this, but; we already know Android Auto is pretty locked down to Googly's services, and requires their apps for the extra functionality. I'm aware of some progress being made to work around it; someone did get Android Auto Running in MicroG as well as AACS and the wonderful reverse engineered OpenAuto

You need either a rooted/modified Android device that has been hacked to eliminate Google's restrictions on only approved AA apps, or something like a raspi or other embedded SBC combined with AACS (https://github.com/tomasz-grobelny/AACS - officially supports only Odroid at the moment, Pi4 support is on my TODO list.)

I want to get https://github.com/tomasz-grobelny/AACS working with my Bolt at some point to confirm some theories I have about the Bolt's implementation of AA.

If you want object detection, classification (car models in your case) as well as tracking them, before getting your feet wet on model selection viz., Yolo, RCNN etc, check out Intel DLStreamer which uses GStreamer as the back end.... It uses Intel OpenVINO for inferencing and custom plugins for detection/classification and tracking also.... Intel has a big model zoo of pre-trained models, which can do the task of identifying the car models..... https://github.com/dlstreamer/dlstreamer

https://github.com/dlstreamer/dlstreamer based on gstreamer