The present and future of post production business and technology

Sloppy Math is good for video analysis?

Sloppy Math is good for video analysis? Better content detection = better metadata for us to use in software.

I’ve been researching technologies over the “Christmas break” and thinking about the future of Assisted Editing, and I have been totally amazed by what already exists in terms of image recognition. So having a more efficient technology for obtaining the raw data to feed to these intelligent image recognition algorithms, means it can all happen faster – i.e. happen for video and not just stills.

In other areas, computer software is fulfilling highly advanced tasks.

Financial modeling and automated trading, way beyond the capability of humans to track and manage. Wired Jan 2011 Algorithms take control of Wall Street.

“Algorithms have become so ingrained in our financial system that the markets could not operate without them.”

In the Smarter than you think – when computers keep watch article in the NYT, computers are expected to (from video content):

Warn of a potential “incident” between warring groups in a prison and alert prison guards;

Watch a hospital room and remind nurses or doctors who fail to wash their hands at an appropriate time (before and after handling a patient);

Warn of a restless patient who is in danger of falling out of bed;

Read a person’s face through a two way “mirror” to detect heart rate and other vital signs (including increasing heart-risk);

Analyze a person’s expressions to gauge emotional response, with very fine grain accuracy (something I’ve mentioned above in the context of generating metadata).

Yes, you read that last one right. Affectiva, a Wlatham, Mass company, has facial recognition softare that can accurately determine the difference between a happy smile, an embarrassed smile and a smirk! The research started as a way to give an autistic child a way of determining the emotions of those around them (a skill autistic children are particularly bad at). The company is now marketing its facial-expression analysis software for market analysis research – gauging customer reaction – to:

“manufacturers of consumer products, retailers, marketers and movie studios. Its mission is to mine consumers’ emotional responses to improve the designs and marketing campaigns of products.”

Going further:

The software “makes it possible to measure audience response with a scene-by-scene granularity that the current survey-and-questionnaire approach cannot,” Mr. Hamilton said. “A director,” he added, “could find out, for example, that although audience members liked a movie over all, they did not like two or three scenes. Or he could learn that a particular character did not inspire the intended emotional response.”

If software can detect emotional responses to movies, it can detect emotional performances and – for documentary/reality/news – detect the emotion in the face to help drive editing.

It will be really interesting to look back from the future and wonder when, exactly, the computers took over!