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 New RFID transponder with large memory and a mobile handheld reader
31.03.2015 | Siemens AG

nachricht UAB Rolls Out New Technology to Help Users Combat Mobile Malware Attacks
31.03.2015 | University of Alabama at Birmingham

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Lizard activity levels can help scientists predict environmental change

Research study provides new tools to assess warming temperatures

Spring is here and ectotherms, or animals dependent on external sources to raise their body temperature, are becoming more active. Recent studies have shown...

Im Focus: Hannover Messe 2015: Saving energy with smart façades

Glass-fronted office buildings are some of the biggest energy consumers, and regulating their temperature is a big job. Now a façade element developed by Fraunhofer researchers and designers for glass fronts is to reduce energy consumption by harnessing solar thermal energy. A demonstrator version will be on display at Hannover Messe.

In Germany, buildings account for almost 40 percent of all energy usage. Heating, cooling and ventilating homes, offices and public spaces is expensive – and...

Im Focus: Nonoxide ceramics open up new perspectives for the chemical and plant engineering

Outstanding chemical, thermal and tribological properties predestine silicon carbide for the production of ceramic components of high volume. A novel method now overcomes the procedural and technical limitations of conventional design methods for the production of components with large differences in wall thickness and demanding undercuts.

Extremely hard as diamond, shrinking-free manufacturing, resistance to chemicals, wear and temperatures up to 1300 °C: Silicon carbide (SiSiC) bundles all...

Im Focus: Experiment Provides the Best Look Yet at 'Warm Dense Matter' at Cores of Giant Planets

In an experiment at the Department of Energy's SLAC National Accelerator Laboratory, scientists precisely measured the temperature and structure of aluminum as...

Im Focus: Energy-autonomous and wireless monitoring protects marine gearboxes

The IPH presents a solution at HANNOVER MESSE 2015 to make ship traffic more reliable while decreasing the maintenance costs at the same time. In cooperation with project partners, the research institute from Hannover, Germany, has developed a sensor system which continuously monitors the condition of the marine gearbox, thus preventing breakdowns. Special feature: the monitoring system works wirelessly and energy-autonomously. The required electrical power is generated where it is needed – directly at the sensor.

As well as cars need to be certified regularly (in Germany by the TÜV – Technical Inspection Association), ships need to be inspected – if the powertrain stops...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

Event News

World Conference On Regenerative Medicine 2015: Registration And Abstract Submission Now Open

25.03.2015 | Event News

University presidents from all over the world meet in Hamburg

19.03.2015 | Event News

10. CeBiTec Symposium zum Big Data-Problem

17.03.2015 | Event News

 
Latest News

Gasoline from a nanoreactor

01.04.2015 | Life Sciences

Saving costs with antifouling coatings

01.04.2015 | Process Engineering

Diversity prevents resistance

01.04.2015 | Agricultural and Forestry Science

VideoLinks
B2B-VideoLinks
More VideoLinks >>>