by Chris Smith, 11 months ago
In addition to posting the full changelog for Android 4.1 Jelly Bean, Google went one step further and released no less than 28 Google I/O Android sessions videos, which are now available on YouTube. Google…
A new patent from Google could potentially change the way we publish videos onto the net in the future. What is this patent exactly? It's known as “automatic large scale video object recognition.”
This object recognition technology works in a similar way to other face recognition techniques, but it takes things a step further. How so? It can actually recognize the difference between a variety of objects, not just human faces.
Whether you are talking about a cat or even a bike, the patent is designed to recognize it. After recognizing an object it then labels it with certain tags. If you are wondering how it does this, there is a special object name repository involved. This database would hold at least 50,000 object names, information and shapes that would allow for easy identification.
Essentially this is just another way to tag and better track videos for things like SEO. Ultimately it makes it easier for YouTube and Google to tag and track videos, but it also could make it easier for us to search for them. The system would still allow for manual tagging of objects and animals, but would do a lot of the work itself through an automated process.
It's unclear when and where exactly object recognition technology will be put into place, though it is pretty much guaranteed to make its way over to YouTube.