Posted by: crudbasher | August 29, 2012

Automatic Object Recognition in Video

Google became the dominant search engine because it automatically was able to rank pages on the net based on their content. The key word here is “automatically”. There are way to many webpages to do it by hand. Trouble is, there is no good way to do it automatically with video.

If you look at the amount of information traveling around the Internet at any one time you would find that video 28.5% of it. Web traffic is the most at 38.0%. What you need to realize though is that video traffic is one of the hardest pieces of information to catalog. Right now videos are cataloged very crudely by humans putting in keywords. Ideally you want a computer to do it automatically but, while computers are getting to be decent at recognizing faces, they are not good at everything else. Well, that might be changing.

From Engadget:

“Google has already been working on patents that could pick out faces and song melodies in our YouTube clips. Now, it might just have the ultimate tool: the technique in a just-granted patent could pick out objects in a video, whether they’re living or not. Instead of asking the creator to label objects every time, Google proposes using a database of “feature vectors” such as color, movement, shape and texture to automatically identify subjects in the frame through their common traits — a cat’s ears and fast movement would separate it from the ball of yarn it’s attacking, for example.”

Now it’s just a patent but I’m betting there is some actual technology behind this. Getting computers to understand video is a very important project for many people so I think this will be solved fairly soon. This then creates a number of interesting possibilities for education.

  1. Every video on YouTube will be searchable for content. This is millions of hours of “free” content for use in classes.
  2. If you are wearing Augmented Reality glasses with a camera in them, you can record everything you see. This is useless though unless it can all be searchable. Imagine being able to replay anything that happens to you in your life. This means your students will be able to replay anything they experience too.
  3. A natural side effect of this will be our memories will become more specialized as we rely on our technology for long term storage of information. We already do it to a certain extent but a generation raised with this technology will be very different from us.

(cc) Emmanual_D.Photography

There are lots of very bad possibilities too. Privacy pretty much goes away. Certain cities right now like London already have cameras pretty much everywhere. Now governments will be able to have a computer make a database of everything we do, everyone we talk to, everything we buy, everything period. Once again society will have to determine acceptable usage for this new technology.



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 )

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: