Yes and no, I think. It isn’t really huge amounts of data, and the patterns aren’t super complex, so a neural network would pick up a lot. But, given how far the signals travel, the intermittent nature of the signals, and how little they can initially be associated with a particular vehicle, I think in most environments associating a particular set of signals with a particular car would require some human field work. Sure, there are circumstances where automated pairing would be trivial (like at a toll booth), but catching signals in the wild and processing by neural net alone might be ok for analyzing traffic patterns while not being enough for surveillance.

Yeah, I don’t know what the range is for picking these signals up, but I know that the detections just scroll on and on on my laptop’s screen when there is any traffic near my house.

I never realized how chatty the world is on the radio spectrum until playing with one of these. From my house, I can see reports from half a dozen water meters (several reporting leaks), readings from wireless weather stations, signals from certain types of remotes, location data from aircraft, and of course bluetooth and wifi signals from phones and homes. The real trick in using this for tracking would be in filtering out all of the information you aren’t interested in.