hardware
NVIDIA introduces Tegra 3 for tablets and phones
NVIDIA has introduced the quad-core Tegra 3 for mobile devices including tablets and phones. This embedded system was formely code-named "Project Kal-El". In addition to the four high-performance main cores, the Tegra 3 comes with a fifth low-power core which is used when high-performance applications are not running, to extend battery life. There is also a new 12-core GeFORCE GPU. The Tegra 3 will provide a powerful new platform for mobile computer vision applications.
Related articles:
Improving smartphone cameras
The U.S. National Science Foundation (NSF) has awarded $450,000 to Colorado-based company FiveFocal to improve the manufacturing of camera modules for mobile phones and other platforms. The grant is primarily targeted to increasing yields, which would reduce costs; however, it is likely that the improved manufacturing process monitoring will lead to higher quality as well. Increasing numbers of apps that require computer vision software are being written for smartphone platforms; higher and more consistent imaging quality will enhance the performance of many of those computer vision apps. A detailed description of the project is included below.
Point Grey announces smallest USB 3.0 camera
Press release from Point Grey
Point Grey, a world leader of advanced digital camera technology, today announced another innovation in imaging with the release of its new Flea3 USB 3.0 camera series.
Measuring just 29 x 29 x 30mm, the FL3-U3 is the smallest USB 3.0 camera in the world and is designed specifically for the demanding requirements of machine and computer vision applications. The first available models are based on monochrome and color versions of the Sony® IMX036, a high-quality CMOS sensor capable of generating 3.2 megapixel images at 60 FPS.
"We are very excited to start production of our first USB 3.0 cameras and begin addressing the huge amount of demand we're seeing for this technology," says Michael Gibbons, Product Marketing Manager. Gibbons adds, "USB 3.0 is rapidly gaining industry acceptance, largely due to its higher bandwidth, improved reliability and architecture, and widespread availability on a variety of hardware platforms."
With a practical limit of 384 MBytes/s, USB 3.0 is almost 10 times faster than USB 2.0 and 5 times faster than FireWire-b. The increased data throughput and improved 4.5 W of power delivery further makes USB 3.0 well-suited for many of the high-speed, multi-megapixel area scan image sensors on the market today. Most laptop, desktop, and embedded systems now provide USB 3.0 ports, which maximizes system compatibility and minimizes the need for add-in PCI or PCI Express interface cards. Easy access to high quality, low cost components like cables and hubs also allows end users to lower the overall cost of their systems.
3D modeling of royal burial sites by drone
Researcher Marijn Hendrickx of the University of Ghent uses a drone to build 3D models of archaeological sites. The 1 kg, 70 cm quadrocopter drone was able to map Scythian burial mounds in the area where Russia, China, Kazakhstan, and Mongolia meet; 3D models of the site were constructed from the images. More information is available at livescience.com.
Boston Dynamics to introduce AlphaDog robot in 2012
Boston Dynamics is working on a successor to its BigDog military robot, to be called AlphaDog. It uses a stereo camera, computer vision, and GPS for navigation; can carry several hundred pounds of gear; and is intended to support a military squad. According to the MIT Technology Review, it will use computer vision to follow a human soldier.
3D eye tracking technology could boost augmented reality
SensoMotoric Instruments' (SMI) binocular eye-tracking glasses provide 3D eye-tracking data superimposed on high-definition (HD) scene camera video. SMI is promoting these glasses primarily for design of package displays, automobile cockpits, printed materials, and user interfaces; however, the eye-tracking technology holds potential for enabling truly immersive augmented reality (AR) applications. More information is available from SMI's press release.
Intel's River Trail boosts computer vision in web apps
Intel has developed an open-source JavaScript extension that enables web applications to exploit parallel processing capabilities of the underlying hardware. The extension, called River Trail, is currently available as a Firefox add-on at github. River Trail enables web applications to run on multiple cores and to use vector processing capabilites. The Intel software is compatible with HTML5 and with WebGL.
Mozilla CTO and JavaScript inventor Brendan Eich told The Register that "The demo shows a 15x speedup over serial JavaScript. It lightens up the ridiculously parallel hardware in modern CPUs and GPUs, for audio, video, image processing, automated voice response, computer vision, 3D gaming, etc. – all written in memory-safe, clean, functional JavaScript, without threads and their data races and deadlocks."
Testing computer vision systems for planetary rovers
Astrium, a European Aeronautic Defence and Space (EADS) company is conducting an 11-day field trial of its Planetary Robotics Vision Ground Processing (PRoVisG) system in Tenerife in the Canary Islands. According to the Astrium website, "Leading-edge computer vision technology will be collected inside and outside Europe to better exploit the image data gathered during future robotic space missions to the moon and the planets." The current trial is taking place in two national parks in Tenerife chosen for their similarity to the landscapes of the Moon and Mars.
Gelsight portable super high resolution 3D imaging
MIT researchers have developed Gelsight, a high resolution 3D imaging system. Gelsight uses a unique "slab of transparent, synthetic rubber, one of whose sides is coated with a paint containing tiny flecks of metal." An object is pressed against the surface of the slab, and the paint-coated side of the slab deforms. Cameras can then photograph the paint-coated side of the result, and "computer-vision algorithms analyze the images" to produce the 3D image. The research team consists of researchers Edward Adelson, Micah Kimo Johnson, Alvin Raj, and Forrester Cole. More information is available in a press release.
Microsoft bundles Kinect SDK with Robotics Developer Studio
According to EE Times, Microsoft has bundled its Kinect software development kit (SDK) with its free Robotics Developer Studio. The SDK would enable access to Kinect's raw data, as well as its gesture-recoginition algorithms. The article also states that Microsoft plans to add direct support for autonomous navigation tasks. Although developers are not allowed to use the Kinect SDK to develop commercial products, nonprofit organizations will be able to add navigational algorithms for maneuvering robots.