Back to Table of contents

Primeur weekly 2012-08-13

Exascale supercomputing

Department of Energy awards $62 million in contracts to accelerate development of 'extreme scale' supercomputers ...

The Cloud

DreamWorks Animation drives innovation with HP Cloud Services ...

DDN and Alliance Technology Group enable data-intensive intelligence & surveillance organisations to economically harness the power of Big Data and Cloud collaboration ...

Applied Math Modeling releases Cloud-based, next-generation data centre design software ...

EuroFlash

Altair RADIOSS structural solver achieves unmatched performance using NVIDIA GPUs ...

UK’s Atomic Weapons Establishment selects Rogue Wave's ThreadSpotter ...

Future Internet PPP - Information Day on Call 2, Objectives 1.8 & 1.9 ...

What makes Paris look like Paris? Carnegie Mellon software finds stylistic core ...

USFlash

UC San Diego team aims to broaden researcher access to protein simulation ...

UC San Diego and Yale awarded collaborative NSF grant for Neuroscience Gateway ...

GPU acceleration of top genomics application with OpenACC promises to help speed delivery of life-saving drugs ...

DataDirect Networks debuts comprehensive management suite to simplify Big Data infrastructure scale up and scale out ...

DataDirect Networks announces rapid uptake of award-winning SFA technology across Australia's research computing community ...

EMC DLm8000 first mainframe virtual tape library to deliver synchronous replication ...

Swinburne to unveil the hidden universe ...

AMD launches first-ever AMD FirePro APU providing a powerful integrated visual computing platform for CAD and media and entertainment work flows ...

SGI reports fourth quarter and fiscal year 2012 financial results ...

Dell helps to power NASA's latest mission to Mars ...

Large private donation launches Institute for Advanced Computational Science at Stony Brook University ...

Computer models calculate systems-wide costs of gene expression ...

XSEDE brings in NCSA's Alan Craig as Digital Humanities Specialist ...

What makes Paris look like Paris? Carnegie Mellon software finds stylistic core

7 Aug 2012 Pittsburgh - Paris is one of those cities that has a look all its own, something that goes beyond landmarks such as the Eiffel Tower or Notre Dame. Researchers at Carnegie Mellon University and INRIA/Ecole Normale Supérieure in Paris have developed visual data mining software that can automatically detect these sometimes subtle features, such as street signs, streetlamps and balcony railings, that give Paris and other cities a distinctive look.

The software analyzed more than 250 million visual elements gleaned from 40,000 Google Street View images of Paris, London, New York, Barcelona and eight other cities to find those that were both frequent and could be used to discriminate one city from the others. This yielded sets of geo-informative visual elements unique to each city, such as cast-iron balconies in Paris, fire escapes in New York City and bay windows in San Francisco.

The discovered visual elements can be useful for a variety of computational geography tasks. Examples include mapping architectural correspondences and influences within and across cities, or finding representative elements at different geo-spatial scales such as a continent, a city, or a specific neighbourhood.

Researchers have presented their findings August 9 at SIGGRAPH 2012, the International Conference on Computer Graphics and Interactive Techniques, at the Los Angeles Convention Center.

Alexei Efros, associate professor of robotics and computer science at CMU, noted that although finding patterns in very large databases - so-called Big Data mining - is widely used, it has so far been limited to text or numerical data.

"Visual Data is much more difficult, so the field of visual data mining is still in its infancy, but I believe it holds a lot of promise. Our data mining technique was able to go through millions of image patches automatically - something that no human would be patient enough to do", stated Alexei Efros, who collaborated with colleagues including Abhinav Gupta, assistant research professor of robotics, and Carl Doersch, a Ph.D. student in CMU's Machine Learning Department. "In the long run, we wish to automatically build a digital visual atlas of not only architectural but also natural geo-informative features for the entire planet."

For this study, the researchers started with 25,000 randomly selected visual elements from city images gathered from Google Street View. A machine learning program then analyzed these visual elements to determine which details made them different from similar visual elements in other cities. After several iterations, the software identified the top-scoring patches for identifying a city. For Paris, those patches corresponded to doors, balconies, windows with railings, street signs - the shape and colour of the signs, not the street names on the signs, and special Parisian lampposts. It had more trouble identifying geo-informative elements for U.S. cities, which the researches attributed to the relative lack of stylistic coherence in American cities with their melting pot of styles and influences.

"We let the data speak for itself", stated Abhinav Gupta, noting the entire process is automated, yet produces a set of images that convey a better stylistic feel for a city than a set of random images.

Carl Doersch said this process requires a significant amount of computing time, keeping 150 processors working overnight. By comparison, art directors for the 2007 Pixar movie "Ratatouille" spent a week running around Paris taking photos so they could capture the look and feel of Paris in their computer model of the city.

In addition to Alexei Efros, Abhinav Gupta and Carl Doersch, the research team included Saurabh Singh, a former research assistant in the Robotics Institute, and Josef Sivic, a researcher at INRIA / Ecole Normale. Supérieure.

More information, including a video, is available on the project web site at http://graphics.cs.cmu.edu/projects/whatMakesParis/
Source: Carnegie Mellon University

Back to Table of contents

Primeur weekly 2012-08-13

Exascale supercomputing

Department of Energy awards $62 million in contracts to accelerate development of 'extreme scale' supercomputers ...

The Cloud

DreamWorks Animation drives innovation with HP Cloud Services ...

DDN and Alliance Technology Group enable data-intensive intelligence & surveillance organisations to economically harness the power of Big Data and Cloud collaboration ...

Applied Math Modeling releases Cloud-based, next-generation data centre design software ...

EuroFlash

Altair RADIOSS structural solver achieves unmatched performance using NVIDIA GPUs ...

UK’s Atomic Weapons Establishment selects Rogue Wave's ThreadSpotter ...

Future Internet PPP - Information Day on Call 2, Objectives 1.8 & 1.9 ...

What makes Paris look like Paris? Carnegie Mellon software finds stylistic core ...

USFlash

UC San Diego team aims to broaden researcher access to protein simulation ...

UC San Diego and Yale awarded collaborative NSF grant for Neuroscience Gateway ...

GPU acceleration of top genomics application with OpenACC promises to help speed delivery of life-saving drugs ...

DataDirect Networks debuts comprehensive management suite to simplify Big Data infrastructure scale up and scale out ...

DataDirect Networks announces rapid uptake of award-winning SFA technology across Australia's research computing community ...

EMC DLm8000 first mainframe virtual tape library to deliver synchronous replication ...

Swinburne to unveil the hidden universe ...

AMD launches first-ever AMD FirePro APU providing a powerful integrated visual computing platform for CAD and media and entertainment work flows ...

SGI reports fourth quarter and fiscal year 2012 financial results ...

Dell helps to power NASA's latest mission to Mars ...

Large private donation launches Institute for Advanced Computational Science at Stony Brook University ...

Computer models calculate systems-wide costs of gene expression ...

XSEDE brings in NCSA's Alan Craig as Digital Humanities Specialist ...