Find Nearby Automated License Plate Readers (ALPR)

They are used to read - and recognize - plates.

The official use is to check if the car is insured, or if a stolen / marked car is going through the road, in both cases the police is dispatched to check on the vehichle

> uses a Raspberry Pi 5, a Halo AI board, and You Only Look Once (YOLO) recognition software to build a “computer vision system that’s much more accurate than anything on the market for law enforcement” for $250

https://github.com/bennjordan/ALPRovingGround

> A simple Python application to test adversarial noise attacks on license plate recognition systems (see my PlateShapez demo) and create an output dataset to train more effective attack models.. small, hardly-noticeable, random gaussian shapes to confuse AI license plate readers

"Flock's gunshot detection microphones will start listening for human voices" (250 comments), https://news.ycombinator.com/item?id=45473698

My hunch is that, on my local journeys, I have seen the majority of cars before, to just see them as generic cars, with none of them special, apart from a few owned by friends and a few idiosyncratic vehicles (tractors, pre-war classic cars and anything else rare).

I could be wrong with most cars being totally new to me, maybe not on the road outside my door, but on the big road that my road joins on to.

My use case is as a cyclist. So that Raspberry Pi will need to be carried somehow. There aren't too many cyclists around in my neck of the woods, therefore, even though I might see all cars as generic boxes, their drivers might see me as 'there is that stupid cyclist again', hopefully to give me space on the road.

We all have to get along on the roads and I don't want any conflict, mostly because I will need to use the same roads again and I wouldn't want to meet someone on the road after some silly road-rage type of incident. Therefore, knowing how many cars are actually new to me would be useful to know.

This applies to so much else, even the birds in the garden, where I can't tell one sparrow from another. It would be great to know which of them are residents and which ones are from out of town. Birds don't wear number plates though.

I live in a small town a ways out of the downtown area, so I thought "they're probably only on the highway where I've seen cameras"... Nope, basically every intersection with a stoplight near me is listed as having four nodes. Much more densely than nearby larger cities on the map even...

I don't like that one bit.

In anticipation of this happening someone should build an open source project that processes data points from these cameras, reconstructs movement, correlates the data with with various public and non-public databases, and provides a searchable user interface that will make the average person shit their pants through combination of panic and disgust when they see it.

Then just wait for the inevitable data leak and let the public track the movements of every politician and lobbyist (by name), correlated with their other activities, as well as track anonymized members of the general public.

The average person won't ever "get it" unless they see a system like that for themselves. That might not be enough either but it would lead to some progress if executed well.