Detecting Surveillance Cameras With The ESP32

These days, surveillance cameras are all around us, and they’re smarter than ever. In particular, many of them are running advanced algorithms to recognize faces and scan license plates, compiling ever-greater databases on the movements and lives of individuals. Flock You is a project that aims to, at the very least, catalogue this part of the surveillance state, by detecting these cameras out in the wild.

The system is most specifically set up to detect surveillance cameras from Flock Safety, though it’s worth noting a wide range of companies produce plate-reading cameras and associated surveillance systems these days. The device uses an ESP32 microcontroller to detect these devices, relying on the in-built wireless hardware to do the job. The project can be built on a Oui-Spy device from Colonel Panic, or just by using a standard Xiao ESP32 S3 if so desired. By looking at Wi-Fi probe requests and beacon frames, as well as Bluetooth advertisements, it’s possible for the device to pick up telltale transmissions from a range of these cameras, with various pattern-matching techniques and MAC addresses used to filter results in this regard. When the device finds a camera, it sounds a buzzer notifying the user of this fact.

Meanwhile, if you’re interested in just how prevalent plate-reading cameras really are, you might also find deflock.me interesting. It’s a map of ALPR camera locations all over the world,  and you can submit your own findings if so desired. The techniques used by in the Flock You project are based on learnings from the DeFlock project. Meanwhile, if you want to join the surveillance state on your own terms, you can always build your own license plate reader instead!

[Thanks to Eric for the tip!]

A man holds a license plate in front of a black pickup (F-150 Lightning) tailgate. It is a novelty Georgia plate with the designation P00-5000. There are specks of black superimposed over the plate with a transparent sticker, giving it the appearance of digital mud in black.

A Deep Dive On Creepy Cameras

George Orwell might’ve predicted the surveillance state, but it’s still surprising how many entities took 1984 as a how-to manual instead of a cautionary tale. [Benn Jordan] decided to take a closer look at the creepy cameras invading our public spaces and how to circumvent them.

[Jordan] starts us off with an overview of how machine learning “AI” is used Automated License Plate Reader (ALPR) cameras and some of the history behind their usage in the United States. Basically, when you drive by one of these cameras, an ” image segmentation model or something similar” detects the license plate and then runs optical character recognition (OCR) on the plate contents. It will also catalog any bumper stickers with the make and model of the car for a pretty good guess of it being your vehicle, even if the OCR isn’t 100% on the exact plate sequence.

Where the video gets really interesting is when [Jordan] starts disassembling, building, and designing countermeasures to these systems. We get a teardown of a Motorola ALPR for in-vehicle use that is better at being closed hardware than it is at reading license plates, and [Jordan] 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.

[Jordan] was able to develop a transparent sticker that renders a license plate unreadable to the ALPR but still plainly visible to a human observer. What’s interesting is that depending on the pattern, the system could read it as either an incorrect alphanumeric sequence or miss detecting the license plate entirely. It turns out, filtering all the rectangles in the world to find just license plates is a tricky problem if you’re a computer. You can find the code on his Github, if you want to take a gander.

You’ve probably heard about using IR LEDs to confuse security cameras, but what about yarn? If you’re looking for more artistic uses for AI image processing, how about this camera that only takes nudes or this one that generates a picture based on geographic data?

Continue reading “A Deep Dive On Creepy Cameras”