Posted by: crudbasher | August 3, 2011

When Computers Can Watch TV

(cc) Ambernectar 13

If you look at the growth of Internet traffic over the last five years the vast majority of the increase has been in video. Stats vary, but Netflix alone accounts for more traffic than any single source. A year ago Youtube said it was getting 24 hours worth of video uploaded every minute. Today it’s about 48 hours a minute.

The problem for search companies like Google is that they really can’t index that information. Of sure we can tag the videos but that is a very crude way of doing it. It’s like taking a movie like The Bourne Identity and describing it as “action, movie, Matt Damon”. It doesn’t say what is actually in it.

Enter DARPA. DARPA is the US military’s research branch. They are responsible for many of the technical innovations we use today including the Internet itself. DARPA is creating a research project to have a computer watch a video and be able to index what it saw. Using computer vision techniques it will be able to pull massive amounts of information and allows someone to search for it. So for example you would be able to ask for videos with a blue BMW car in it and it will pull up every matching scene.

What this means for Education will be huge. As teachers we need content and examples. Using techiques like this we will have access to the mass of video information now floating around the Internet. It will increase our information by orders of magnitude.

Of course it also has some negative uses too. It enables much more monitoring of people. A city fitted with a network of cameras (New York, London) will be able to build a database of every move you make.

Right or wrong, this is coming. As usual, it will be up to society to decide how far this will go. Let’s hope we make some wise choices (although our track record lately is not inspiring).

  • Visual context searching

    tags: graphics videos software web3.0 context technology

    • DARPA this month said it will detail a new system it would like to see built known as the Visual Media Reasoning (VMR) program. The main idea is to develop an advanced software program that can “turn ‘dumb’ unstructured, ad hoc photos and video into true visual intelligence.”
    • “The computer vision/image understanding field has matured greatly over the last 40 years and is currently seeing rapid new advances driven by private sector trends such as augmented reality apps on smart phones and the integration of powerful image search capabilities into the popular internet search engines. Rather than recreate the wheel, VMR will exploit these current and emerging advances by employing ensembles of best-of-breed image recognition techniques, from 3D object extraction to color signatures to auto-indexing of image content and more.”

Posted from Diigo. The rest of my favorite links are here.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s


%d bloggers like this: