All posts by nicolemmens

Computers doing it for you.

Our last blog is an odd tangent of some sorts as it isn’t really about Non Destructive Testing, although it’s something I really wanted to include in our blog series: Computer Vision.
In a way it is related, everything is being automated and N.D.T. is no exception to this rule.

If you’re a reader from our academic institute (and studying electro mechanics), you’re currently receiving lessons and lab sessions about vision systems. In my own opinion these lessons only touch the subject very superficially on a fundamental soft-/hardware level and don’t provide a true reflection of what’s currently possible.

Within industry you might immediately think of quality control, checking for visual defects on cookies or if all bottles have a bottle cap. On the other side Hollywood might have you think anything is possible with AI and vision systems, like Iron Man’s “Jarvis” or what the terminator is capable of. So, what is the state of the union within vision systems today?

t2%20%2816%29From our own experience; it’s not all that easy and straightforward as you might think. We’ve been messing around with basic object recognition and boy, that stuff is all very, very young and in full development. If you want to make a complex vision system today, prepare to deal with a lot of scattered open source projects and basic binary kits because there’s no true easy and straightforward package out there, yet.

1XNYvfGqsv

Last year Google (who else) made some huge strides forward in object recognition which they showcased at “ImageNet’s visual recognition challenge”.   By using something they call a “neural network” they can now swiftly and accurately recognize random (unknown) objects within various scenes. Which is pretty amazing since most vision systems out there today require you to “teach” them the specific object to look for first. Even then scaling, rotation and lighting can mess everything up. So in some sorts they’ve achieved the basic object recognition skills of a 3-year old for AI systems, which might sound a little low brow but certainly isn’t! You can read about the competition and what it really implies here: http://googleresearch.blogspot.be/2014/09/building-deeper-understanding-of-images.html . With the prospect of self-driving cars you kind of expect them to be experts in vision systems anyway right?

The video below is a TED talk that discusses this neural network a little more in detail. Basically they fed some supercomputer a HUGE load of labeled image data from which it can now determine what it sees in an image. Of course object recognition is only a small part of what vision systems truly hold within, discussing everything would require a blog of its own. But observing that this is another leap towards a ‘seeing’ AI that in the future can truly understand and see relations is a pretty amazing thing.
Paraphrased From the talk:

Like the little child the computer doesn’t just say cat and bed but says it’s a cat laying on a bed

So back to NDT: if QC is fully automated and you can’t even see if the AI was wrong after the check, would you still trust it?

Advertisements

True invisibility.

As mentioned in my last post, we’re not seeing invisibility cloaks any time soon. But at Rochester University (USA), they have been working on devices that truly allow you to ignore stuff and directly look at what lies behind.

fea-cloaking
Most methods of making things invisible rely on bending the light around the object you wish to obscure, like the negative refraction discussed previously that required complicated and expensive meta-materials. This method also bends light, but just uses cheap, off she shelf optic lenses you can get anywhere.

The image below shows their cheapest and simplest design. The concept here is that light is bent and forced to pass trough a fine focal area in the middle, ignoring all that lies around it. It can be scaled up or down to whatever size is desired, but is only applicable to “dough-nut shapes”, they do mention to have developed methods that obscure objects entirely without this requirement but these are more complicated.

2014-03-07-howell-cloaking-200-crop-630x228This method, according to them, is extraordinary as it is the first device to provide such extended cloaking for visual light.

From a continuous range of viewing angles, the hand remains cloaked, and the grids seen through the device match the background on the wall (about 2 m away), in color, spacing, shifts, and magnification.

Here’s the link to the full scientific paper: Paper

One can quickly see this method is applicable on two levels, either to hide something you don’t want to see, or to particularly see something that would normally be blocked. I can see this being used as a new category of N.D.T. in the future.  While researching the topic i found someone who proposed it to be used for surgeons, to block out their own hands and tools so they can better see the organs they’re operating on. Sounds like an amazing idea to me !

What to you think? Is it a viable tool? Or is the featured four lens system too complicated to ever be used anywhere?

Here’s the full article from the university itself: Link

Hollow Man

Ok so, so far I’ve been talking about seeing what is normally hidden without actually touching, removing or breaking anything. But what’s the state of affairs at the other side of this spectrum? Invisibility.

Camouflage is a universal trait of any living thing thing out there and humans have always been preoccupied with its developpement, from using the fur from other animals to stealth bombers. The ultimate camouflage would ofcourse be pure invisibility, so yeah, how close are we to getting an invisibility cloack?

I found this old TEDInvisible-Man-SFX talk from 2013, which you can watch here if you wish: TED talk video. I’ll give you the quick rundown tough:

Basically it mentions that H.G. Wells wasn’t that far off with his theory in the book “The Invisible Man”.  The talk might disappoint you however, no true visual invisibility is achieved. The theory they propose does have some interesting arguments though. “Meta-materials” that provide a negative refraction index.

A short refresher:
Refraction is the principle of different materials bending light in different ways, normally the refraction number is positive, measured against a complete vacuum as a reference. (Which has a refraction number of 1, air has 1.000293.) The most famous example to illustrate this phenomena is a straw in a glass of water, seeming oddly ‘broken’ and shifted as shown on the left in the image below. Negative refraction would result in the even more distorted straw deformation seen in the glass on the right.
negative_refraction-640x369In theory the property of negative refraction should allow you to bend light in the opposite direction to which you’d normally expect it to go, essentially opening the door to invisibility. If you really want to go deeper into the physics of it I can start you off with these Wikipedia articles on the topic: http://en.wikipedia.org/wiki/Negative_refraction and http://en.wikipedia.org/wiki/Snell%27s_law.

For now the guys from the TED talk haven’t been able to apply it to visible light, but they have been successful in the domain of radio waves.  Applying these materials as a cover could be used to make radio towers (like the ones for your mobile phone) invisible to each other, dramatically reducing mutual interference. The meta-material allows electromagnetic waves to be emitted from within but makes incoming radio waves just ‘pass trough’ the antenna.

This again shows how messing  around with a certain technology or theory can result in major advances in other areas of technology than intended.

The only thing close to an actual invisibility cloak i could find on the net make use of complicated suits, using camera’s  strapped to the back and either LCD/ LED technology ‘clothing’ or using a projector placed in front of the subject. The entire setup is hardly subtle and is very far away from providing true invisibility of any sorts in my opinion.

In short: invisibility cloaks, on our way but far from actually getting there.

So, there’s an evident ethical question to be posed here, do we really want invisibility cloaks to ever be a thing? It didn’t end well for the protagonist in Well’s book, but i won’t ruin the plot for you. Harry potter might have only used his invisibility cloak for doing good in the scenes that were shown to us, but what about all those other times we weren’t told about?!

So, do you personally see more advantages than disadvantages in this technology or do you think this is just another thing that just shouldn’t ever be a thing? Also, where do you think it could actually be handy?

I think this research should just continue, i can see many benefits but I’m going deeper into that in a future blog.
I’d get very paranoid however. But in the end aren’t we all already walking around with devices that could, in principle, listen to everything we hear, say and see ourselves to some extent? I don’t think covering an invisible person with a post-it would do that much.

SAMSUNG
As a personal extra: what use of invisibility in fiction is your favorite? Mine was in the movie ‘Hollow Man’ also shows the concept of invisibility,if you haven’t seen it, I recommend it as an entertaining watch !

Imaging systems and your privacy.

Part 2: Seeing your thoughts.

Upon researching the previous privacy blog i stumbled upon some other stuff too.

For instance, have you at any point ever wondered why that police helicopter just kept going in circles above your neighborhood? Well, as it turns out they found out a rather clever trick to discover possible illegal  marijuana plantations.

Using heat camera’s they scan entire neighborhoods for unusual heat signatures, weed plantations are easy to spot as they usually clearly stand out on the special footage.

article-2461412-18C0914600000578-186_634x356Or as in the picture on the left, the plantation in this flat was just literally glowing with an absurd amount heat. (Corresponding article here.)

It’s another method to see whats going on inside people’s private property. But unlike the technology used in the first blog I personally don’t feel this one really invades privacy as it doesn’t pierce trough the surface of your home… What’s your opinion on this method?

On a way different level they are experimenting with stuff you can only dream of:
Looking into someone’s brain !

In the following Youtube clip researchers show video fragments to  test subjects while extracting brain activity data using fMRI. Subsequently they use this data to re-create the original footage by matching the original data with a huge database of random video’s (youtube clips). Sort of like how you can now use Google images by uploading a picture yourself and getting the same or similar pictures as a search result.

The footage in the red square is the original, shown to the test subject.
The footage in the green squares is the reconstructed video (3 different iterations are shown), which is composed by averaging out the video’s from the blue squares, which are possible matches.

Obviously the resulting  footage is currently relatively raw and inaccurate. The Youtube video above stems from 2011, but if you look at a video from only a year prior, you can see they have made huge advancements already.

If they ever get this right, they might be able to ‘fully’ visualize a persons thoughts and dreams.

So obviously this technology can go many ways. Both bad and good, obviously by the title of this blog i’m hinting towards possible privacy abuse when used against someones will. But it’s easy to see it has many possible positive applications too.

What do you see for the future of this technique? If it reaches it’s full potential, and provides a pretty clear image, will it mostly be used for evil or good?

Say now for instance, should the law be allowed to use this on key witnesses ?
Could it be used as a lie detector on inmates? What in the case of people who ended up in a coma or vegetative state.
Should the family be allowed to hook them up on such a machine, just to see what’s still going on in there?

I know it’s very hypothetical  and personal, it also covers a fairly ‘general’ side of privacy, but I’d still like your opinion…

Read the abstract and full text of the related research paper here:
http://www.cell.com/current-biology/abstract/S0960-9822%2811%2900937-7#Summary

NDT and art.

This is a short intermezzo blog, as always people seem to find a bridge in between technology and art. Well actually, to be honest, it’s not hard to imagine X-ray NDT technology being used for art, as it is just a special kind of photography after all.

The following TED talks is a video about Nick Veasey, who has devoted his life to creating awesome X-ray pictures of interesting situations and objects.

What surprised me is the amount of work that goes into creating these pictures. For instance, i wasn’t aware that for an X-ray of a ‘mini’ you’d have to disassemble the entire car and take pictures of every individual component ,only to reassemble the whole later…  I also feel slightly cheated about the fact that most of the ‘people’ you see are actually just skeletons.

Nevertheless, awesome stuff to look at. If you had access to his installation for a day, what would you scan?

I figure i’d scan a magic 8-ball, always wondered what goes on in there.

magic-8-ball-shirt