-
The automated analysis of the video image will be the next big innovation
0
February 10th, 2010videoRemember that the character can be a gardener in there? "I like watching TV," was his famous phrase. The problem with the videos more business is that we produce a large amount of images impossible to see, especially those taken by security camera. And there is no risk around that want to watch them, either.
The problem is that trying to find one or two events in all concrete actions that the images is not easy. As an example, take the story in today's NY Times that mentions how the army is buried under a huge pile of video images of their Predator planes that are flying over Pakistan and Afghanistan. The situation will only get worse, as new models drone will send flows of data from dozens of cameras in a few years.
The story has already been said about how the video drones' feeds are available for anyone with some knowledge of minor software – effective monitoring of the channels are scrambled, but the video streams are not. This is unreliable because many people need to see what they are broadcasting and the military has not been able to deploy the viewing figures in these streams.
In the Times article, a group of soldiers based in Hampton, Virginia, sits in front of the screen and see real-time, and then make screengrabs available to the right people via computer chat rooms. I hope for the sake of everyone involved that these chat rooms are encrypted, but the article does not say.
So how to implement our automated Chance Gardner? There are a couple of technologies that can help, but not easy or cheap to implement. One is the telestrator, the device popularized by John Madden and Monday Night Football, where a noted commentator on the screen and see doodles colored to highlight what is happening. Those Madden and that professionals use are very expensive, but there are dozens of products available for the PC market, with some freeware products like VIDEOMAG producer.
The telestrators are good, but again, someone must be watching video and electronic doodling. You need more than the fast forward button to do this – ideally, you want some kind of automated system that can identify actionable moments on video. This is what the next class of products is called intelligent image analysis. They have computers to see the sequence of activities and highlight the fact that a person can return to and later review.
This is what stoplift.com company is doing with its analysis of retail systems for payment. Normally, a store retailing install video cameras above each aisle and cash register what the spell is doing as items pass through the point of sale scanners. There are all types of fraud that can be used as "sweethearting" (an accomplice is giving free points that are not scanned) and it appears that you are scanning a bar code when the item has just passed around and above the Bagger. So that is needed is a system that links the retail outlet and you can make when such items are not touched up in the registry. I got to see a demonstration last week and this was way cool. The company claims its software can have a period of six months of return on investment and substantially reduce the cost of stolen goods. And the good news is that nobody has to do all the security tapes to see a few moments of love.
Tags: automated video, image analysis, video image analysis