Search results

You can always go aftermarket / DIY this

Yes. Waze, ABRP, Google Maps, and Apple Maps all send meta data to the HUD. See page 52 onwards here for what the HUD can do: https://developer.apple.com/download/files/CarPlay-Developer-Guide.pdf| (android auto is similar but I cant find the documentation)

Try Waze? Just to rule out Google Maps being the issue.

1) have you tried different navigation apps 2) do you have an iPhone you can try as well ? 3 possibilities - 1) App isn’t sending the HUD meta data over 2) Android isn’t sending the meta data over 3) Car is receiving but not correctly processing the HUD meta data testing 1) different nav apps...

Have any of you been able to find aftermarket (or official) colored versions of outer key fob trim? I’m not a huge fan of these overmold style ones. I’ve been resisting just making one myself…

This is indeed just a one-off personal side project. There are no plans to productize or distribute (the BOM cost alone would make this infeasible!).

So technically its not the Kalman part that’s most computationally taxing it’s the o(n3) Hungarian matching I have on top (and now we’re firmly in mumbo jumbo tech speak land :)) I don’t really expect this to be an issue unless if for some reason there are dozens of tracks.

Found the engineer :) The blog post reflects an earlier version of the code. The architecture is now fully decoupled with independent pipelines. Camera thread (60 fps) —> writes to ring buffer Ring buffer —> inference thread (variable FPS - in practice 60 fps) —> mailbox Ring buffer + mailbox...

I would've added it as an option to my build if it was available! But alas... but then again now I have something I have full control of and can customize however I'd like powered by state of the art hardware + ML models :) I suspect changing their stack to Android Automotive OS probably had...

Oh ditto - yeah I'm in the US so my car has the adaptive matrix thing turned off as well. PITA.

Ha - no there's 0 hackery going on here. In fact 0 car-side software changes. This is basically just a fancy dash cam. What are you thinking? If I had control over the headlight module I'd probably light up detected collision risks.

Everything runs off an Nvidia Orin Nano sitting in the frunk. Using a YOLO model trained on thermal data. See blog post here (directionally correct; I’ve made a bunch of changes since that aren’t reflected): https://www.sahouh.com/build-logs/part-5-inferencing-at-60-fps For those interested...

ha! if you’ve got a few thousand labeled thermal images of kangaroos, I can bake them into the model. the current model’s trained on: 1) People 2) Wild hogs 3) Coyotes 4) Deer 5) Raccoon 6) Bikes Basically just about everything you might come across in California

Custom project. Designed for safety / animal collision avoidance at night. Demo video (software still a work in progress): Camera location: