New Mobile Phone Usage Detection Cameras AU

[TestOne]

Hi Guys,

found y'all in Google and thought this might be the best place to ask some questions about IR cameras and your thoughts on some new technology being currently trialed in NSW Australia.

acusensus.com has started installing cameras that will photograph through the front windscreen of a vehicle on public roads and assess whether the driver is using a mobile phone illegally. Legal arguments aside, their website says that their cameras are able to avoid the issues of sunlight glare on the windscreen and take high resolution, high speed images of the interior of the vehicle through the front windscreen. I'd like to know what technology you think is likely being implemented by these cameras to take these high quality photos in both the day and the night.

Does it look like these cameras are just using infrared lights to take these images? What about the daytime photos, would they be taken with infrared lighting as well or just ambient light? Due to road regulations I don't think these cameras use a standard flash due to the fact the cameras are photographing the vehicle from in front and a flash could blind the driver....

Below are a couple of links to articles containing some of the released images taken by these cameras. I'll be very interested to know what technology you think these cameras employ to take their photos.

https://www.caradvice.com.au/712107/mobile-phone-camera-trial/
https://www.news.com.au/technology/innovation/motoring/on-the-road/new-mobile-detection-cameras-to-be-turned-on-in-sydney/news-story/b9ed01a2b97804db1819cee397573502
 

Cheers.
 

[eKretz]

My guess looking at the images is they're using the tech commonly referred to as "night vision."  So a sensor that detects near infrared and probably a fairly powerful near infrared flash-type illuminator - the light from which would be almost completely invisible to the human eye. In addition,  it would appear that the flash and camera are downward-facing, and the vehicle occupants' faces aren't exposed to either the camera flash or the lens. That raises the issue of how they could possibly positively I.D. the driver though.

[TestOne]

Thanks for the reply.

That raises the issue of how they could possibly positively I.D. the driver though.

Apparently EVERY vehicle on the roadway will be monitored by a few different cameras as well as radar. I believe that firstly the vehicles are identified/followed with radar and initially license plate details captured at a distance, then as the vehicle approaches the high res images are captured, then AI is used to process the image and detect if there is any illegal use of the mobile phone.

infrared flash-type illuminator

I've found a link below to some images captured during the day. It looks to me as though these do not use IR, just the ambient daylight? What do you think? 
https://www.dailymail.co.uk/news/article-6498985/Mobile-phone-cameras-catch-11-000-drivers-breaking-law-wheel.html

 

[Ultrapurple]

I concur that it looks as though the images are taken in near-IR. As we know, glass is opaque to LWIR and may or may not transmit MWIR. I certainly wouldn't expect the clarity of image we're seeing in the samples from a MWIR camera unless it was a real top-end (hi-res) device.

As far as I can see the impressive thing is the way the system designers have managed to achieve fairly even, flat lighting without significant reflection from the windscreen. Presumably the illumination is offset and the angles carefully calculated. As far as the daylight images go, although there is some reflection I get the distinct impression they're using polarisation to reduce the effect. (If you have the money there's no reason why you shouldn't have a number of cameras in a cluster, each with slightly different polarisation, so you can select the best image in every circumstance - this makes up for the fact that the polarisation of reflected sunlight changes as the day progresses, partly due to the simple geometry of the setup).

The image recognition back-end is also very clever.

My car's windscreen has an integral filter layer that reflects UV, which is not an unusual feature. I wonder how long it'll be before someone has the bright idea to coat windscreens with an IR-reflective layer? I believe it's already being done to some number plates in an attempt to reduce the effectiveness of speed cameras.

We're quite a long way from thermal infrared here...

[TestOne]

I wonder how long it'll be before someone has the bright idea to coat windscreens with an IR-reflective layer?

Not an option, at least in Australia as the national standards prevent ANY film or material being added to the front windscreen. Manufacturers could include the feature in their windscreens provided they pass all the other requirements but nothing can be applied to the windscreen aftermarket.

We're quite a long way from thermal infrared here...

What do you mean by this?..

[Ultrapurple]

I wonder how long it'll be before someone has the bright idea to coat windscreens with an IR-reflective layer?

Not an option, at least in Australia as the national standards prevent ANY film or material being added to the front windscreen. Manufacturers could include the feature in their windscreens provided they pass all the other requirements but nothing can be applied to the windscreen aftermarket.

Understood. Several other countries have similar regulations for very sensible safety reasons. My thoughts were along the lines of a manufacturer-applied coating of some sort, very like the integral UV-reflecting coating I described. Sorry for the confusion.

We're quite a long way from thermal infrared here...

What do you mean by this?..

EEVblog has many forums and I am acknowledging that my comments/speculation on near-infrared are straying slightly off-topic for the thermal imaging forum. I don't think it's a particular problem in this instance - many other threads have meandered through a wide range of subjects as they develop - but I'm just noting I'm aware of it.

[2N3055]

Or they simply use polarizer filter on normal camera. With polarizer filter on my SLR you can eliminate reflections...

[eKretz]

No, polarization on a normal visible light camera won't work at night without a flash which would be a nonstarter as already mentioned by the O.P. - I think Ultrapurple is probably right,  polarizing filter on near-IR is the most likely.

Near-infrared is a different wavelength than thermal (LWIR) infrared, which is what Ultrapurple was mentioning, so yes it's a little off-topic.

[Ultrapurple]

Hokay, another look at this.

Briefly, the Fresnel Equations tell us that the reflections from an air-glass interface (or any two transmissive mediums) will have a degree of polarisation related to the angle of incidence. In plain English this means that if you shine unpolarised light at a windscreen then the reflected light will be polarised one way more than the other, depending on the various angles. This works at any wavelength, LWIR, ultraviolet, whatever. If you use a polarising filter on a camera (or eyeball) looking at the reflection, then you will be able to find a position where the filter matches the reflection best (you'll see more reflected light) or the transmitted light best (you'll see what's behind the glass).

Conversely, if you shine polarised light onto the windshield, you'll get more or less transmission vs reflection as you change the polarisation of the light source.

Sunlight is only very slightly polarised (this is down to atmospheric effects and both the polarisation angle and amount of polarisation vary during the day). So it's likely that at I could adjust a camera and polarising filter for minimum reflection at (say) 9am but by later in the morning it would require readjustment for optimum results. That's why I mentioned an array of cameras in an earlier post - one optimised for (say) each couple of hours.

At night things are different, as one can have control of the polarisation of the light. You know the likely angle (or at least orientation) of the car windscreen so you can arrange the polarisation for maximum transmission and minimum reflection. You can also place the emitter(s) where they won't be directly reflected from the glass. Furthermore, you can put a suitable polarising filter on the camera so that any light scattered into the 'wrong' polarisation will be rejected.

As a side issue, I believe that using relatively narrow band light (eg from a LED source) makes all of this easier still, as you're then dealing with a much smaller band of frequencies and can optimise the optical elements accordingly.

The bottom line is that if you have reasonable control of the environment it's not too hard to arrange near-IR lighting to give excellent see-through-glass capability, at least most of the time. Daylight - which contains a lot of near-IR - complicates matters.

It's also worth contemplating that one only releases one's best shots for publicity purposes. We have no way of knowing whether 99% of the images are as good as the samples shown, or if they were one-in-a-million lucky shots.

Moving back to longer wavelengths, has anyone got any experience with polarising filters for LWIR? Do they even exist?