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 Micropatterning OLEDs using electron beam technology
27.04.2016 | Fraunhofer-Institut für Organische Elektronik, Elektronenstrahl- und Plasmatechnik FEP

nachricht Quantum computing closer as RMIT drives towards first quantum data bus
18.04.2016 | RMIT University

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Nuclear Pores Captured on Film

Using an ultra fast-scanning atomic force microscope, a team of researchers from the University of Basel has filmed “living” nuclear pore complexes at work for the first time. Nuclear pores are molecular machines that control the traffic entering or exiting the cell nucleus. In their article published in Nature Nanotechnology, the researchers explain how the passage of unwanted molecules is prevented by rapidly moving molecular “tentacles” inside the pore.

Using high-speed AFM, Roderick Lim, Argovia Professor at the Biozentrum and the Swiss Nanoscience Institute of the University of Basel, has not only directly...

Im Focus: 2+1 is Not Always 3 - In the microworld unity is not always strength

If a person pushes a broken-down car alone, there is a certain effect. If another person helps, the result is the sum of their efforts. If two micro-particles are pushing another microparticle, however, the resulting effect may not necessarily be the sum their efforts. A recent study published in Nature Communications, measured this odd effect that scientists call “many body.”

In the microscopic world, where the modern miniaturized machines at the new frontiers of technology operate, as long as we are in the presence of two...

Im Focus: Tiny microbots that can clean up water

Researchers from the Max Planck Institute Stuttgart have developed self-propelled tiny ‘microbots’ that can remove lead or organic pollution from contaminated water.

Working with colleagues in Barcelona and Singapore, Samuel Sánchez’s group used graphene oxide to make their microscale motors, which are able to adsorb lead...

Im Focus: ORNL researchers discover new state of water molecule

Neutron scattering and computational modeling have revealed unique and unexpected behavior of water molecules under extreme confinement that is unmatched by any known gas, liquid or solid states.

In a paper published in Physical Review Letters, researchers at the Department of Energy's Oak Ridge National Laboratory describe a new tunneling state of...

Im Focus: Bionic Lightweight Design researchers of the Alfred Wegener Institute at Hannover Messe 2016

Honeycomb structures as the basic building block for industrial applications presented using holo pyramid

Researchers of the Alfred Wegener Institute (AWI) will introduce their latest developments in the field of bionic lightweight design at Hannover Messe from 25...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

The “AC21 International Forum 2016” is About to Begin

27.04.2016 | Event News

Soft switching combines efficiency and improved electro-magnetic compatibility

15.04.2016 | Event News

Grid-Supportive Buildings Give Boost to Renewable Energy Integration

12.04.2016 | Event News

 
Latest News

Expanding tropics pushing high altitude clouds towards poles, NASA study finds

06.05.2016 | Earth Sciences

IU-led study reveals new insights into light color sensing and transfer of genetic traits

06.05.2016 | Life Sciences

Thievish hoverfly steals prey from carnivorous sundews

06.05.2016 | Life Sciences

VideoLinks
B2B-VideoLinks
More VideoLinks >>>