Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Algorithm enables computers to identify actions much more efficiently

14.05.2014

Techniques from natural-language processing enable computers to efficiently search video for actions

With the commodification of digital cameras, digital video has become so easy to produce that human beings can have trouble keeping up with it. Among the tools that computer scientists are developing to make the profusion of video more useful are algorithms for activity recognition — or determining what the people on camera are doing when.

At the Conference on Computer Vision and Pattern Recognition in June, Hamed Pirsiavash, a postdoc at MIT, and his former thesis advisor, Deva Ramanan of the University of California at Irvine, will present a new activity-recognition algorithm that has several advantages over its predecessors.

One is that the algorithm's execution time scales linearly with the size of the video file it's searching. That means that if one file is 10 times the size of another, the new algorithm will take 10 times as long to search it — not 1,000 times as long, as some earlier algorithms would.

Another is that the algorithm is able to make good guesses about partially completed actions, so it can handle streaming video. Partway through an action, it will issue a probability that the action is of the type that it's looking for. It may revise that probability as the video continues, but it doesn't have to wait until the action is complete to assess it.

Finally, the amount of memory the algorithm requires is fixed, regardless of how many frames of video it's already reviewed. That means that, unlike many of its predecessors, it can handle video streams of any length (or files of any size).

The grammar of action

Enabling all of these advances is the appropriation of a type of algorithm used in natural language processing, the computer science discipline that seeks techniques for interpreting sentences written in natural language.

"One of the challenging problems they try to solve is, if you have a sentence, you want to basically parse the sentence, saying what is the subject, what is the verb, what is the adverb," Pirsiavash says. "We see an analogy here, which is, if you have a complex action — like making tea or making coffee — that has some subactions, we can basically stitch together these subactions and look at each one as something like verb, adjective, and adverb."

On that analogy, the rules defining relationships between subactions are like rules of grammar. When you make tea, for instance, it doesn't matter whether you first put the teabag in the cup or put the kettle on the stove. But it's essential that you put the kettle on the stove before pouring the water into the cup. Similarly, in a given language, it could be the case that nouns can either precede or follow verbs, but that adjectives must always precede nouns.

For any given action, Pirsiavash and Ramanan's algorithm must thus learn a new "grammar." And the mechanism that it uses is the one that many natural-language-processing systems rely on: machine learning. Pirsiavash and Ramanan feed their algorithm training examples of videos depicting a particular action, and specify the number of subactions that the algorithm should look for. But they don't give it any information about what those subactions are, or what the transitions between them look like.

Pruning possibilities

The rules relating subactions are the key to the algorithm's efficiency. As a video plays, the algorithm constructs a set of hypotheses about which subactions are being depicted where, and it ranks them according to probability. It can't limit itself to a single hypothesis, as each new frame could require it to revise its probabilities. But it can eliminate hypotheses that don't conform to its grammatical rules, which dramatically limits the number of possibilities it has to canvass.

The researchers tested their algorithm on eight different types of athletic endeavor — such as weightlifting and bowling — with training videos culled from YouTube. They found that, according to metrics standard in the field of computer vision, their algorithm identified new instances of the same activities more accurately than its predecessors.

Pirsiavash is particularly interested in possible medical applications of action detection. The proper execution of physical-therapy exercises, for instance, could have a grammar that's distinct from improper execution; similarly, the return of motor function in patients with neurological damage could be identified by its unique grammar. Action-detection algorithms could also help determine whether, for instance, elderly patients remembered to take their medication — and issue alerts if they didn't.

Abby Abazorius | newswise
Further information:
http://www.mit.edu

Further reports about: Massachusetts Technology algorithm identified identify problems

More articles from Information Technology:

nachricht Superfast fluorescence sets new speed record
27.07.2015 | Duke University

nachricht Two crystals are better than one
22.07.2015 | The Agency for Science, Technology and Research (A*STAR)

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Quantum Matter Stuck in Unrest

Using ultracold atoms trapped in light crystals, scientists from the MPQ, LMU, and the Weizmann Institute observe a novel state of matter that never thermalizes.

What happens if one mixes cold and hot water? After some initial dynamics, one is left with lukewarm water—the system has thermalized to a new thermal...

Im Focus: On the crest of the wave: Electronics on a time scale shorter than a cycle of light

Physicists from Regensburg and Marburg, Germany have succeeded in taking a slow-motion movie of speeding electrons in a solid driven by a strong light wave. In the process, they have unraveled a novel quantum phenomenon, which will be reported in the forthcoming edition of Nature.

The advent of ever faster electronics featuring clock rates up to the multiple-gigahertz range has revolutionized our day-to-day life. Researchers and...

Im Focus: Superfast fluorescence sets new speed record

Plasmonic device has speed and efficiency to serve optical computers

Researchers have developed an ultrafast light-emitting device that can flip on and off 90 billion times a second and could form the basis of optical computing.

Im Focus: Unlocking the rice immune system

Joint BioEnergy Institute study identifies bacterial protein that is key to protecting rice against bacterial blight

A bacterial signal that when recognized by rice plants enables the plants to resist a devastating blight disease has been identified by a multi-national team...

Im Focus: Smarter window materials can control light and energy

Researchers in the Cockrell School of Engineering at The University of Texas at Austin are one step closer to delivering smart windows with a new level of energy efficiency, engineering materials that allow windows to reveal light without transferring heat and, conversely, to block light while allowing heat transmission, as described in two new research papers.

By allowing indoor occupants to more precisely control the energy and sunlight passing through a window, the new materials could significantly reduce costs for...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

3rd Euro Bio-inspired - International Conference and Exhibition on Bio-inspired Materials

23.07.2015 | Event News

Clash of Realities – International Conference on the Art, Technology and Theory of Digital Games

10.07.2015 | Event News

World Conference on Regenerative Medicine in Leipzig: Last chance to submit abstracts until 2 July

25.06.2015 | Event News

 
Latest News

Tool making and additive technology exhibition: Fraunhofer IPT at Formnext

31.07.2015 | Trade Fair News

First Siemens-built Thameslink train arrives in London

31.07.2015 | Transportation and Logistics

California 'rain debt' equal to average full year of precipitation

31.07.2015 | Physics and Astronomy

VideoLinks
B2B-VideoLinks
More VideoLinks >>>