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 Laser process simulation available as app for first time
23.11.2015 | Fraunhofer-Institut für Lasertechnik ILT

nachricht Powering the next billion devices with Wi-Fi
19.11.2015 | University of Washington

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: Innovative Photovoltaics – from the Lab to the Façade

Fraunhofer ISE Demonstrates New Cell and Module Technologies on its Outer Building Façade

The Fraunhofer Institute for Solar Energy Systems ISE has installed 70 photovoltaic modules on the outer façade of one of its lab buildings. The modules were...

Im Focus: Lactate for Brain Energy

Nerve cells cover their high energy demand with glucose and lactate. Scientists of the University of Zurich now provide new support for this. They show for the first time in the intact mouse brain evidence for an exchange of lactate between different brain cells. With this study they were able to confirm a 20-year old hypothesis.

In comparison to other organs, the human brain has the highest energy requirements. The supply of energy for nerve cells and the particular role of lactic acid...

Im Focus: Laser process simulation available as app for first time

In laser material processing, the simulation of processes has made great strides over the past few years. Today, the software can predict relatively well what will happen on the workpiece. Unfortunately, it is also highly complex and requires a lot of computing time. Thanks to clever simplification, experts from Fraunhofer ILT are now able to offer the first-ever simulation software that calculates processes in real time and also runs on tablet computers and smartphones. The fast software enables users to do without expensive experiments and to find optimum process parameters even more effectively.

Before now, the reliable simulation of laser processes was a job for experts. Armed with sophisticated software packages and after many hours on computer...

Im Focus: Quantum Simulation: A Better Understanding of Magnetism

Heidelberg physicists use ultracold atoms to imitate the behaviour of electrons in a solid

Researchers at Heidelberg University have devised a new way to study the phenomenon of magnetism. Using ultracold atoms at near absolute zero, they prepared a...

Im Focus: Climate Change: Warm water is mixing up life in the Arctic

AWI researchers’ unique 15-year observation series reveals how sensitive marine ecosystems in polar regions are to change

The warming of arctic waters in the wake of climate change is likely to produce radical changes in the marine habitats of the High North. This is indicated by...

All Focus news of the innovation-report >>>



Event News

Fraunhofer’s Urban Futures Conference: 2 days in the city of the future

25.11.2015 | Event News

Gluten oder nicht Gluten? Überempfindlichkeit auf Weizen kann unterschiedliche Ursachen haben

17.11.2015 | Event News

Art Collection Deutsche Börse zeigt Ausstellung „Traces of Disorder“

21.10.2015 | Event News

Latest News

Harnessing a peptide holds promise for increasing crop yields without more fertilizer

25.11.2015 | Agricultural and Forestry Science

Earth's magnetic field is not about to flip

25.11.2015 | Earth Sciences

Tracking down the 'missing' carbon from the Martian atmosphere

25.11.2015 | Physics and Astronomy

More VideoLinks >>>