press release

Tweet Follow @compvision

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.

Tweet Follow @compvision

New Visconti™2 Family Supports Up to Four High-Resolution Color Cameras to Detect Pedestrians, Highway Lanes and Traffic Lights and Signs

SAN JOSE , Calif., October 13, 2011 — Toshiba America Electronic Components, Inc., (TAEC)*, a committed leader that collaborates with technology companies to create breakthrough designs, today announced the second-generation of its Visconti series of image recognition processors for automotive applications, Visconti™2 (TMPV7500). The processors recognize lanes, vehicles and pedestrians using a camera-based vision system. The Visconti2 devices support up to four 1.3 megapixel color cameras, making them suitable for applications requiring color identification, such as the detection of traffic lights and signs. They incorporate four separate media processing engines (MPEs) and up to six image processing accelerators to enhance image recognition performance.

The Visconti2 devices' image processing accelerators use Toshiba's own histogram of oriented gradients (HOG) technology to enable real-time pedestrian detection at both day and night, thanks to its ability to sense lighting changes and small deformations. When connected to four cameras, the Visconti2, TMPV7506XBG, device can simulate a bird's-eye view based on image data captured by the cameras for use in parking assistance applications.

Product Specifications

Tweet Follow @compvision

Now supports large projects with ability to process up to 1,000 laser scans and unlimited points

Herndon, Virginia — September 6, 2011 — ClearEdge3D today released EdgeWise™ Plant 2.0, software that automates the extraction of complex CAD pipe geometry from 3D laser scanned data, dramatically reducing time to create accurate as-built 3D industrial plant models.

Press release from FR Vision AB

Scientists release unique app for video enhancement
"DollyCam is the best software for automagic video stabilization"

August 3, Linköping, Sweden. Scientists at Linköping University in Sweden recently launched DollyCam for iPhone and iPad. The app is based on patent pending technology that automatically stabilizes video captured with CMOS video cameras, such as found
in new mobile phones, and tablet devices. The result is astonishing and lets amateurs create professional movies without expensive equipment.

Anyone who has tried to capture video with a mobile phone knows how easily the result becomes shaky and wobbly, with skewed objects and an overall amateurish feeling. The poor result is caused by the rolling-shutter technology used in low-end consumer cameras, and by the fact that you hold the camera in your hand. Professional filmmakers use global-shutter cameras, rails and dollys for smooth camera movements.

DollyCam is based on leading research in computer vision. The unique algorithm uses three-dimensional data from the gyroscope and accelerometer sensors on the iOS device to correct tilted objects and remove wobble. A video stabilizer then adds smoothness and makes the movie stable. DollyCam is also adaptive and adjusts its parameters dynamically to the movie processed. The scientists have conducted a blind user study among students on campus. The study demonstrated that participants preferred DollyCam output to that of its competitors.

"With this app you get a professional and smooth video from a cheap consumer camera", says Per-Erik Forssén, assistant professor at Linköping University who presented the
underlying algorithm at the international IEEE Conference on Computer Vision and Pattern Recognition in San Francisco 2010.

The scientists recently founded the company FR Vision AB, with support from the Innovation Office at the University. DollyCam is their first product, but the company also intends to disseminate the technique as professional products for video editing packages like Adobe After Effects and Apple Final Cut, as well as application programming interfaces that allow integration in other products.

"Our vision is to integrate our technology in hardware from big players like Apple, Sony Ericsson, and Samsung, to let a bigger audience experience better movies", says Erik Ringaby, doctoral student at the Department of Electrical Engineering at Linköping University. "We also hope service providers like Google and Facebook will be interested in licensing our technology."

Source:http://www.fr-vision.se/press_release.pdf

Press release from York University

An unmanned aerial vehicle (UAV) is flying around York University this week as part of an experiment designed to develop 3D technology that will provide a detailed picture of what’s happening in any city – whether it’s a concert or a crime, a traffic jam or the creative route a driver takes to avoid it.

Weighing just 1.3 kg and measuring 80cm x 80cm x 30cm, the Aeryon Scout is flying no more than 60 metres off the ground, with a video camera focused on buildings, walkways, and trees, and the activity around them.

“Mapping of urban environments is typically done from aircraft flying high above the city, or vehicles on the ground (i.e. Google Streetview). But a lot of the important details lie somewhere in between,” says James Elder, a professor in both the Department of Computer Science & Engineering and the Department of Psychology at York University. “This vehicle – the Aeryon Scout – can acquire the high-resolution imagery of building facades required to reconstruct the detailed 3D structure of our cities.”

The research team has developed proprietary computer vision algorithms and a geospatial web mapping system to detect and track people and vehicles in real-time video streamed from city cameras, and then to project them as avatars into 3D city models. This allows the life of the city to be experienced in a natural 3D context, and viewed from any angle through web browsers. This is augmented by visual intelligence about the scene – for example, recognition of objects and activities as well as things like vehicle speed.

Press release from SRI International on Thursday July 7, 2011, 1:00 pm EDT

SRI International Technology in Google Talk for Android Tablets

Video Stabilization Software from SRI Embedded into Chat Applications

MENLO PARK, Calif. — July 7, 2011 — As tablets allow users to connect with the world, there is increasing demand for new features that match our fast-paced lifestyle. With video chats becoming more common, people want the option to "walk and talk." Yet, picture quality and the viewer experience can be poor. When people are moving and talking during a video chat, the transmitted images can appear shaky and hard to watch.

Now, for the first time, tablet users have access to SRI's 2D video stabilization software, which has been embedded into Google Talk™ applications and is available on Android™ 3.0+ devices.

"Google has selected SRI technology for stabilizing video chats and conferences on Google Talk, making video conversations with a stable picture an anytime, anywhere experience for tablet users," said Norman Winarsky, Ph.D., vice president, SRI Ventures. "As leaders in vision and video research, we continue to enhance consumers' positive user experience. This mobile device innovation is a reflection of SRI's strategic research and development, focused on meeting important market needs."

Video technology researchers at SRI Sarnoff began working on the stabilization problem in the early 1990s, when they developed a way to electronically stabilize and enhance surveillance videos. Their seminal work in motion estimation led to the development of 2D video stabilization software that compensates for motion in a scene by eliminating it and keeping a person's face as the central focus. This patented technology provided the mathematical foundation for SRI Sarnoff's Acadia family of vision products, used in security, surveillance, and car safety applications.

Press release from Boulder Imaging

Boulder, Colorado – NEWS RELEASE, July 4, 2011 – Boulder Imaging, a world leader in high performance quality inspection, machine vision, and high speed imaging solutions, announced today that Neil Vanasse has joined the company as a Senior Optical Solutions Engineer. Mr. Vanasse is an optical and mechanical engineer with over fifteen years of experience. Mr. Vanasse will be designing imaging solutions around the company’s flagship product lines Vision Inspectort™ Intelligent Machine Vision and Quazar High Performance Digital Video Recorder (HPDVR)™.

Press release from Embedded Vision Alliance

More than fifteen leading technology companies — including some of the largest semiconductor companies — have joined forces to speed the adoption of computer vision capabilities in electronic products. The ability of machines to see and understand their environments — what we call “embedded vision” — promises to transform the electronics industry with products that are more intelligent and aware of their environments, and to create significant new markets for electronic equipment and components. A new consortium, called the Embedded Vision Alliance (www.embedded-vision.com), will enable the proliferation of embedded vision technology by providing design engineers with information, practical know-how, and industry standards.

“Adding computer vision to embedded systems creates phenomenal new products, markets, and opportunities,” according to Jeff Bier, president of BDTI. “Just look at the Microsoft KinectTM, which added vision to the Xbox 360TM—it became the fastest-selling consumer electronics device in history, shipping more than 10 million units in 5 months. But that’s just a small part of the story. From automobiles that prevent accidents to security cameras that prevent crimes, embedded vision will proliferate across a multitude of markets.”

Press release from U.S. Bureau of Engraving and Printing

The Bureau of Engraving and Printing (BEP) has developed a free downloadable application (app) to assist the blind and visually impaired denominate US currency. The app is called EyeNoteTM. EyeNoteTM is a mobile device app designed for Apple iPhone (3G, 3Gs, 4), and the 4th Generation iPod Touch and iPad2 platforms, and is available starting today through the Apple iTunes App Store.

EyeNoteTM uses image recognition technology to determine a note’s denomination. The mobile device’s camera requires 51 percent of a note’s scanned image, front or back, to process. In a matter of seconds, EyeNoteTM can provide an audible or vibrating response, and can denominate all Federal Reserve notes issued since 1996. Free downloads will be available whenever new US currency designs are introduced. Research indicates that more than 100,000 blind and visually impaired individuals currently own an Apple iPhone.

Press release from New York University

New York University’s Courant Institute of Mathematical Sciences has received a grant from the U.S. Office of Naval Research (ONR) to develop a bird-sized, self-flying plane that could navigate through both forests and urban environments.

The Courant Institute shares the $4.5 million, 5-year grant with MIT, Carnegie Mellon University (CMU), and Harvard University.

“The plane would be about the size of a crow, and, like a bird, would use vision to navigate, but it would use orientable propellers and not flap its wings.” explained Yann LeCun, a professor at NYU’s Courant Institute.

The work will rely, in part, on a technology that emulates the visual system of animals called Convolutional Networks, which mimics the neural network in the mammalian visual cortex and can be trained to quickly interpret the world around it. The vision system will run on a new type of computer chip that uses a “dataflow” architecture. Dubbed NeuFlow, the new chip will enable Convolutional Networks and other computer perception algorithms to run on very small and lightweight devices hundreds of times faster than a conventional computer.