[anon_cow1111]

You assumed the camera was capturing a photo of the car viewed from the side where the full speed is apparent (and ironically where the plate will not even be visible).

Most cameras point down the length of the road and the "speed" that the camera sees is only a fraction of that. You can record a video with a merely-ok phone and probably see most plate numbers assuming the lighting isn't terrible. Good luck getting a phone camera to work at night with an LED flash though

(oh and also, this assumes you want to catch people speeding, to capture every plate number you would just put the camera near a slow area like a bend or stop sign)

[shiftpgdn]

I assure you the motion blur, even looking down the same plane (parallel) to the car will not be able to capture the plate, even in decent light on video alone. Go try to take video yourself of a car driving by in full daylight.

[londons_explore]

The obvious approach is to just train your numberplate recognition algorithm with blurred plates. Since the blur is almost equal across the whole plate, and nearly all cars are moving in the same direction, you aren't really losing much information. Sure, it might be hard for a human to read, but for a deep learning algorithm I don't think it's actually any harder.

But there are other approaches too - like putting a 99 cent novelty zoom lens on the front of your camera to capture more light for your region of interest, allowing you to use shorter exposure times. Or an infrared strobe light that flashes once per frame (most numberplates are retroreflective, so IR strobes work really well).