I’ve seen the number of induction coils increase drastically over the years in The Netherlands. They are quite easily recognizable, as there’s typically a solar panel on a pole, that appears to provide power to the system.
Considering there’s a wide variety of vehicles on the road, surely each variant must have (slightly) different characteristics when passing over the coil; especially when in a specific place at a specific time.
And given that they are situated at highway exits (see picture) or after entrances, and road users unable to exit and enter elsewhere, it would be trivial to track the bulk of a vehicle’s trip.
This in context of ALPRs (in different forms) being in place at strategical locations (large junctions or at bridges or tunnels, and parking), and the address of vehicle’s owner; you’d be able to connect the dots, and end up with a pretty complete picture.
That is in a vacuum, but with ALPRs at strategic points, it’s possible to connect the license plate to a series of readings along the way, and would similarly allow correlation to prior trips (be it with a slightly different characteristic that day). As there’s many readings along the way, it should also be possible to filter out large inconsistencies; or with some clever machine learning algorithms, be possible to correlate such inconsistencies with reasonable certainty. Unless multiple cars, that consistently drive head-to-tail the entire trip, create a reading similar to a truck (also with regards to speed), I think it’s quite easy to discern the two categories. On the highway itself each lane has its own coil, so even if a truck had space to drive over the edge of another coil, the primary coil would also be significantly affected. Even the simplest of metal detectors can modulate output based on induction (the beep changing in pitch), so why would recent (~2019) specialty equipment only be able to output a boolean value?