Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:


Algorithm enables computers to identify actions much more efficiently


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:

Further reports about: Massachusetts Technology algorithm identified identify problems

More articles from Information Technology:

nachricht Graphene teams up with two-dimensional crystals for faster data communications
06.10.2015 | ICFO-The Institute of Photonic Sciences

nachricht Simple detection of magnetic skyrmions
06.10.2015 | Sonderforschungsbereich 668

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Physicists shrink particle accelerator

Prototype demonstrates feasibility of building terahertz accelerators

An interdisciplinary team of researchers has built the first prototype of a miniature particle accelerator that uses terahertz radiation instead of radio...

Im Focus: Simple detection of magnetic skyrmions

New physical effect: researchers discover a change of electrical resistance in magnetic whirls

At present, tiny magnetic whirls – so called skyrmions – are discussed as promising candidates for bits in future robust and compact data storage devices. At...

Im Focus: High-speed march through a layer of graphene

In cooperation with the Center for Nano-Optics of Georgia State University in Atlanta (USA), scientists of the Laboratory for Attosecond Physics of the Max Planck Institute of Quantum Optics and the Ludwig-Maximilians-Universität have made simulations of the processes that happen when a layer of carbon atoms is irradiated with strong laser light.

Electrons hit by strong laser pulses change their location on ultrashort timescales, i.e. within a couple of attoseconds (1 as = 10 to the minus 18 sec). In...

Im Focus: Battery Production: Laser Light instead of Oven-Drying and Vacuum Technology

At the exhibition BATTERY + STORAGE as part of WORLD OF ENERGY SOLUTIONS 2015 in Stuttgart, the Fraunhofer Institutes for Laser Technology ILT and for Ceramic Technologies and Systems IKTS will be showing how laser technology can be used to manufacture batteries both cost- and energy-efficiently.

In the truest sense, it’s all about watts at the Dresden-based Fraunhofer Institute for Ceramic Technologies and Systems IKTS and the Aachen-based Fraunhofer...

Im Focus: New Sinumerik features improve productivity and precision

EMO 2015, Hall 3, Booth E06/F03

  • Drive optimization called automatically by the part program boosts productivity
  • Automatically switching the dynamic values to rapid traverse and interpolation...
All Focus news of the innovation-report >>>



Event News

EHFG 2015: Securing healthcare and sustainably strengthening healthcare systems

01.10.2015 | Event News

Conference in Brussels: Tracking and Tracing the Smallest Marine Life Forms

30.09.2015 | Event News

World Alzheimer`s Day – Professor Willnow: Clearer Insights into the Development of the Disease

17.09.2015 | Event News

Latest News

Graphene teams up with two-dimensional crystals for faster data communications

06.10.2015 | Information Technology

Laser-wielding physicists seize control of atoms' behavior

06.10.2015 | Physics and Astronomy

Flipping molecular attachments amps up activity of CO2 catalyst

06.10.2015 | Life Sciences

More VideoLinks >>>