Have vision models started offering better alternatives for such use cases? It's a genuine question; it's been a while since I last looked.
There is an entire spectrum of models, from something like Mask-RCNN, U-Net family upto something like Meta's SAM, which you can use without even training.
That said, there are not that many shapes of speedometer and wheels, and the view point is likely controlled, so your old school method is probably the better way ;)
Is it better to look in the PyTorch community, or that's where some Tensorflow approaches shine? (CUDA is ok)
https://www.youtube.com/watch?v=Nnpm-rJfFjQ
The accuracy is probably quite bad, when looked at individual manipulations, but the overall result is jaw dropping - even, if it's only a demonstration
Wouldn't re-using Meta's SAM (Segment Anything Model) be sufficient here? (which is freely available and, I think, free to use?) Or do you think you need to build your own model specifically for detection bills/sheets of paper?
In my domain of metrology, this part isn't acceptable:
> you will get a model that can predict the exact edges of every input image.
Prediction is a nice way to limit the space I have to consider for a proper edge detection, but usually it's better to just go straight to something more deterministic.
Still fun to learn about Hough transforms, canny edge detection, and all that 1990s computer vision though!