Embedded Vision Insights: August 12, 2014 Edition

Dear Colleague,

After having wrapped up publication of the videos of technical presentations from the May Embedded Vision Summit, we're now about halfway through publishing that event's product demonstration videos. In auditioning them, I'm reminded of the breath and depth of practical computer vision educational content that they (and the event they came from) represent. AMD, for example, demonstrated heterogenous processing of vision algorithms, while Analog Devices discussed its processors' face detection, character recognition and pattern recognition capabilities.

ARM also demonstrated heterogenous processing, specifically in the form of facial analysis and gesture interface algorithms accelerated on the company's GPU cores via OpenCL. Bluetechnix and inrevium AMERICA both showcased time-of-flight sensors, representing one of the three common 3D camera approaches. And Cadence's demonstrations highlighted face detection and real-time image processing, while CogniVue's application focuses spanned both ADAS and consumer electronics designs.

I encourage you to take a few minutes and check out the above-mentioned videos, as well as keeping an eye out for those still to come. And of course, don't forget to mark your calendars for next year's Embedded Vision Summit, which promises to raise the quality bar even further. In past newsletters, I'd indicated that the event would take place on April 30; it's recently been rescheduled to May 12, 2015 (still at the Santa Clara California Convention Center), thereby enabling us to provide you with more technical sessions and more (and bigger) technology workshops the prior day.

I'm also happy to report that the Alliance has added nearly a dozen new members in just the past few months; many of their company descriptions (along with all-important links to their websites for more information) can be found on the Alliance member company overview page. One of them, Aspera, has already published an interesting and informative technical article on network protocol alternatives for optimizing bandwidth and latency, which I commend to your inspection. And of course, while you're on the Alliance website, make sure you check out all the other great new content published there in recent weeks. Thanks as always for your support of the Embedded Vision Alliance, and for your interest in and contributions to embedded vision technologies, products and applications. Whenever you come up with an idea as to how the Alliance can better service your needs, you know where to find me.

Brian Dipert
Editor-In-Chief, Embedded Vision Alliance

Embedded Vision Summit Technical Presentation: "Tools for 'Democratizing' Computer Vision," Jayan Eledath, SRI International
Jayan Eledath, Program Director at SRI International, presents the "Tools for 'Democratizing' Computer Vision" tutorial within the "Algorithm Development Techniques and Tools" technical session at the October 2013 Embedded Vision Summit East. Computer vision has matured to a point where it is beginning to be widely deployed in several real-world applications. This has led to significant growth in the number of vision algorithm and application developers and their communities. However, this growth has resulted in a vast and cluttered landscape of algorithms, many of which have limited capabilities. What is needed, is an efficient means of assessing the performance of these algorithms across imaging domains, and of identifying the best algorithms for specific applications. Under the DARPA Visual Media Reasoning program, SRI has developed automated performance characterization (APC) tools for just this purpose.

OpenCV: Accelerated Computer Vision using GPUs
OpenCV (the Open Source Computer Vision Library) is an open-source BSD-licensed library that includes hundreds of computer vision algorithms. In this webinar from NVIDIA's Shalini Gupta, learn how this powerful library has been accelerated using CUDA on NVIDIA GPUs. A downloadable set of presentation slides in PDF format, along with a downloadable version of the video, are also available.

More Videos

Mobile Photography's Developing Image
Still photos and videos traditionally taken with standalone cameras are increasingly being captured by camera-inclusive smartphones and tablets instead. And the post-capture processing that traditionally required a high-end computer and took a lengthy amount of time can now also take place near-immediately on a mobile electronics device, thanks to the rapidly improving capabilities of embedded vision technology. More

Sustained Growth Set for the Latin American Video Surveillance Market
The Latin American video surveillance equipment market is forecast to see annual average growth rates of over 14%. This is despite ongoing economic uncertainty and civil unrest in Brazil, Latin America’s largest economy, according to recently published estimates from IHS Inc. More

More Articles

Chinese Manufacturer Seeks Vision Expertise to Solve Engineering Challenges

Texas Instruments Surpasses Shipment of 15 Million SoCs, Enabling the Automotive Industry to Redefine Advanced Driver Assistance Systems

SoftKinetic Leverages Its Advanced Technology and World-Class Freescale Silicon to Bring 3D Gesture Recognition to Automotive Infotainment Systems

Imagination’s New Generation PowerVR Series6XT Architecture Delivers Up to 50% Higher Performance and Advanced Power Management

NVIDIA Slides Supercomputing Technology Into the Car with Tegra K1

More News