←back to thread

509 points nullpxl | 5 comments | | HN request time: 0.608s | source

Hi! Recently smart-glasses with cameras like the Meta Ray-bans seem to be getting more popular. As does some people's desire to remove/cover up the recording indicator LED. I wanted to see if there's a way to detect when people are recording with these types of glasses, so a little bit ago I started working this project. I've hit a little bit of a wall though so I'm very much open to ideas!

I've written a bunch more on the link (+photos are there), but essentially this uses 2 fingerprinting approaches: - retro-reflectivity of the camera sensor by looking at IR reflections. mixed results here. - wireless traffic (primarily BLE, also looking into BTC and wifi)

For the latter, I'm currently just using an ESP32, and I can consistently detect when the Meta Raybans are 1) pairing, 2) first powered on, 3) (less consistently) when they're taken out of the charging case. When they do detect something, it plays a little jingle next to your ear.

Ideally I want to be able to detect them when they're in use, and not just at boot. I've come across the nRF52840, which seems like it can follow directed BLE traffic beyond the initial broadcast, but from my understanding it would still need to catch the first CONNECT_REQ event regardless. On the bluetooth classic side of things, all the hardware looks really expensive! Any ideas are appreciated. Thanks!

1. Bender ◴[] No.46078016[source]
Semi-related question. Is there a method to print a picture on a t-shirt that can only be viewed by a camera and not be the naked eye? If so I would like to print images on the front and back of the shirt that would get the glasshole or cell phone cameras banned from their platforms.
replies(4): >>46078203 #>>46080689 #>>46085295 #>>46085307 #
2. downboots ◴[] No.46078203[source]
Infrared LEDs, or a green screen if you have enough access
3. avidiax ◴[] No.46080689[source]
You could make a moire pattern, but it would probably be pretty hard to get it flat enough on a shirt, and it wouldn't be distinct enough to get interpreted by AI.
4. thenthenthen ◴[] No.46085295[source]
I saw some painting a while a go, looked just like random dots, so I took a picture with my smartphone and that revealed a portrait! Pretty amazing, must have been some moire thing indeed
5. Intralexical ◴[] No.46085307[source]
Compare human cone cell spectral sensitivity to the camera modules inside the glasses. [0][1]

Usually digital cameras have some major differences from human eyes, particularly near UV and IR. Find dyes with spectral albedo that integrates to the same strengths for (most) humans' cones, but not for the glasses.

Though human eyes have pretty good dynamic range, and some degree of variation. Maybe add dithering around the edges.

[0]: https://commons.wikimedia.org/wiki/File:Cone-fundamentals-wi...

[1]: https://www.strollswithmydog.com/camera-spectral-sensitivity...