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.
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
Cloud technology: Dynamic certificates make cloud service providers more secure
15.01.2018 | Technische Universität München
New discovery could improve brain-like memory and computing
10.01.2018 | University of Minnesota
On the way to an intelligent laboratory, physicists from Innsbruck and Vienna present an artificial agent that autonomously designs quantum experiments. In initial experiments, the system has independently (re)discovered experimental techniques that are nowadays standard in modern quantum optical laboratories. This shows how machines could play a more creative role in research in the future.
We carry smartphones in our pockets, the streets are dotted with semi-autonomous cars, but in the research laboratory experiments are still being designed by...
What enables electrons to be transferred swiftly, for example during photosynthesis? An interdisciplinary team of researchers has worked out the details of how...
For the first time, scientists have precisely measured the effective electrical charge of a single molecule in solution. This fundamental insight of an SNSF Professor could also pave the way for future medical diagnostics.
Electrical charge is one of the key properties that allows molecules to interact. Life itself depends on this phenomenon: many biological processes involve...
At the JEC World Composite Show in Paris in March 2018, the Fraunhofer Institute for Laser Technology ILT will be focusing on the latest trends and innovations in laser machining of composites. Among other things, researchers at the booth shared with the Aachen Center for Integrative Lightweight Production (AZL) will demonstrate how lasers can be used for joining, structuring, cutting and drilling composite materials.
No other industry has attracted as much public attention to composite materials as the automotive industry, which along with the aerospace industry is a driver...
Scientists at Tokyo Institute of Technology (Tokyo Tech) and Tohoku University have developed high-quality GFO epitaxial films and systematically investigated their ferroelectric and ferromagnetic properties. They also demonstrated the room-temperature magnetocapacitance effects of these GFO thin films.
Multiferroic materials show magnetically driven ferroelectricity. They are attracting increasing attention because of their fascinating properties such as...
08.01.2018 | Event News
11.12.2017 | Event News
08.12.2017 | Event News
19.01.2018 | Materials Sciences
19.01.2018 | Health and Medicine
19.01.2018 | Physics and Astronomy