Hacker News Reader

Comment by fortran77 | Hacker News Reader

I was working on a project like this and we relied on the fact that the IR filter on most cameras was a retro reflector. Remove the IR filter and the camera will be harder to find. I think the technique here also depends on the IR filter’s characteristics.

View on HN

That's a good point. I'm not sure how the removal of the IR filter will affect this work. I mentioned some prior work from the physics side [1] in another comment that explores the reflection characteristics in more detail. I don't think they explored the IR filter contribution as well, so this could be an interesting direction.

[1] https://ieeexplore.ieee.org/document/8790792

IR cut filters used in smartphone-style cameras are typically reflective.

Installing an absorptive IR cut filter on top of the lens would decrease the amount of reflected light, and might hinder your approach. Those are pretty cheap to buy, so you could try it out pretty easily.

The key is they're _retroreflective_.

From this paper:

> Specifically, the hiddencamera embedded in the object reflects the incoming laser pulses at a higher intensity than its surroundings due to an effect called lens-sensor retro-reflection. This occurs when almost all light energy impacting an object is reflected directly back to the source (see Section 2.2). These unexpectedly high-intensity reflections from hidden cameras cause certain regions of the ToF sensor to be “saturated” and appear as black pixels. LAPD processes these saturated areas to automatically identify the hidden camera and its location and displays it on the user’s smartphone screen.

The filter/sensor itself doesn't need to be retroreflective. The fact that it's sitting at the focus of a lens makes it retroreflective.

Nevertheless, if you block all the ~850nm IR light from reaching the lens, then there cannot be any retro reflection at this wavelength, meaning the ToF cannot see anything.

Yes, I agree. I believe military-grade optics detection systems use multiple wavelengths, and some even use short bursts of visible light, making it harder to block.

We were trying to detect audience members filming at live events and in movie theatres, esp. premieres and film festivals (and this was some time ago, when studios, etc, cared more about this). It worked pretty well, even in the early 2000s. I suspect you could do much better today with some "AI" behind it.

Reply on news.ycombinator.com