MessageToEagle.com

New Supercomputer ‘Sees’ Well Enough To Drive A Car Someday

16 September 2010

MessageToEagle.com - Navigating our way down the street is something most of us take for granted; we seem to recognize cars, other people, trees and lampposts instantaneously and without much thought.

In fact, visually interpreting our environment as quickly as we do is an astonishing feat requiring an enormous number of computations—which is just one reason that coming up with a computer-driven system that can mimic the human brain in visually recognizing objects has proven so difficult.

Now Eugenio Culurciello of Yale’s School of Engineering & Applied Science has developed a supercomputer based on the human visual system that operates much more quickly and efficiently than ever before.

Dubbed NeuFlow, the system takes its inspiration from the mammalian visual system, mimicking its neural network to quickly interpret the world around it. Culurciello presented the results Sept. 15 at the High Performance Embedded Computing (HPEC) workshop in Boston, Mass.

The system uses complex vision algorithms developed by Yann LeCun at New York University to run large neural networks for synthetic vision applications. One idea—the one Culurciello and LeCun are focusing on, is a system that would allow cars to drive themselves.

In order to be able to recognize the various objects encountered on the road—such as other cars, people, stoplights, sidewalks, not to mention the road itself—NeuFlow processes tens of megapixel images in real time.

NeuFlow is a supercomputer that mimics human vision to analyze complex environments, such as this street scene. (Image: Eugenio Culurciello/e-Lab)

The system is also extremely efficient, simultaneously running more than 100 billion operations per second using only a few watts (that’s less than the power a cell phone uses) to accomplish what it takes bench-top computers with multiple graphic processors more than 300 watts to achieve.

“One of our first prototypes of this system is already capable of outperforming graphic processors on vision tasks,” Culurciello said.

Culurciello embedded the supercomputer on a single chip, making the system much smaller, yet more powerful and efficient, than full-scale computers.

“The complete system is going to be no bigger than a wallet, so it could easily be embedded in cars and other places,” Culurciello said.

Beyond the autonomous car navigation, the system could be used to improve robot navigation into dangerous or difficult-to-reach locations, to provide 360-degree synthetic vision for soldiers in combat situations, or in assisted living situations where it could be used to monitor motion and call for help should an elderly person fall, for example.

Note: This story has been adapted from a news release issued by Yale University

See also:
"The Most Profound Mystery In All Of Science" - Dark Energy

Follow MessageToEagle.com for the latest news on Facebook and Twitter !

Don't Miss Our Stories! Get Our Daily Email Newsletter

Enter your email address:


Once you have confirmed your email address, you will be subscribed to the newsletter.

Recommend this article:

No Empty Space In The Universe - Dark Matter Fills The Intergalactic Space

Black Gaps In The Sky Puzzle Astronomers

Mysteries Of A Dark Universe

Peculiar Nebulous Objects

Countless Trillions Of Glowing Orbs That Illuminate The Universe

Mysterious Dark Matter

Mysterious Flares Emitting From Sagittarius A

Subscribe To Our Space, Astronomy, Astrophysics, Earth and Xenology News!

Grab the latest RSS feeds right to your reader, desktop or mobile phone.

Subscribe to RSS headline updates from:
Powered by FeedBurner

Go to - MAIN PAGE

Copyright @ MessageToEagle.com All rights reserved.
Go to - MAIN PAGE


Other Popular Articles

Abnormal Star Discovered In The 'Forbidden Zone'
A team of astrophysicists from Germany, France and Italy have discovered in the constellation Leo is an old star. The star's existence raised at once many questions for scientists. The object is definitely not as its "contemporaries" that appeared immediately after the Big Bang event.

Star Changes Into An Incredible Diamond Planet - with video
How can a star change into a diamond planet? Astronomical discoveries show that what sounds like science fiction is actually reality...

Astrophysicist Resolves Paradox With Radio Millisecond Pulsars
Celestial objects known as pulsars are still full of secrets. It is takes time and many efforts to learn all their secrets. Previous studies reached the paradoxical conclusion that some millisecond pulsars are even older than the universe itself. It was time to resolve this paradox.

Astronomical Mystery: Giant Alien Planet Orbiting Three Suns
Binary stars are well-known and even trinary systems may be common but most of them are crowded together and thus, difficult to find and study. Additionally, it has long been considered they are inhospitable to planets...

The Eyes Of A Future Alien Astronomer - What Will They See?
Have you ever wondered what the Universe will look like for a future alien astronomer?
It will in fact be entirely different from what it is today. One trillion years from now, an alien astronomer in our galaxy will have great difficulties figuring out how the universe began.
The Milky Way will have merged with the Andromeda galaxy to form the Milkomeda galaxy. Many of its stars, including our Sun, will have burned out.

Violent Dragon Clash Billions Of Years Ago
NGC 5907 is sometimes called the "Splinter" or Knife Edge Galaxy because of its unusual appearance. It is a spiral galaxy lying in the Dragon constellation, about 40 million light-years from Earth that could have been formed through a gigantic collision of galaxies, 8 to 9 billion years ago.

Researchers Developed A Very Accurate Map Of Milky Way's Magnetic Field
The Milky Way is hard to map because we are sitting on the edge of the galaxy looking through it. However, we know that spiral galaxies like the Milky Way have magnetic fields that follow a particular pattern so we were able use polarised light to map the magnetic fields...


W3Counter