Embedded Vision Insights: September 4, 2013 Edition

Dear Colleague,

The Embedded Vision Summit East, a technical educational forum for product creators interested in incorporating visual intelligence into electronic systems and software, will be held in one month, on October 2. It will take place at the Regency Inn and Conference Center in Westford, Massachusetts. Details of the event program are coalescing, and I have a few more updates to share with you in this edition of Embedded Vision Insights.

Back in late July, I passed along the details of the "Blackfin Embedded Vision Starter Kit Hands-on Workshop," presented by Alliance members Analog Devices, Avnet Electronics Marketing and BDTI and taking place from 8:30AM-1:30PM on October 3, the day after the Embedded Vision Summit East. I'm happy to announce that a second half-day workshop has now been added to the October 3 program. The "Smarter Vision Hands-On Workshop" co-presented by Avnet and Xilinx will run from 12:00PM-5:00PM, and will introduce SoC application development with a specific focus on embedded vision using the Xilinx Vivado Design Suite to target the Xilinx Zynq-7000 All Programmable SoC. For more information on both sessions, including online registration forms, please see the workshops page on the Alliance website.

We've also published an initial set of technical presentations (and presenters) for the Summit, with more to come in the coming days. In some cases, the sessions will be updated versions of top-rated talks given at the April Embedded Vision Summit San Jose (such as "Targeting Computer Vision Algorithms to Embedded Hardware" by Mario Bergeron of Avnet); in other cases, the top-rated presenters will be the same, but the topics will be brand new (for example, "Embedded Lucas-Kanade Tracking: How it Works, How to Implement It, and How to Use It" by Goksel Dedeoglu of Texas Instruments). Regularly monitor the speakers and presentations pages on the website for updates. And don't delay in registering, as attendance spots are limited and interest is strong (and will undoubtedly increase in the coming 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. I welcome your emailed suggestions on what the Alliance can do better, as well as what else the Alliance can do, to better service your needs.

Brian Dipert
Editor-In-Chief, Embedded Vision Alliance

Moving Object Detection Through Background Subtraction
Jeff Bier, founder of the Embedded Vision Alliance, interviews Goksel Dedeoglu, Manager of Embedded Vision R&D at Texas Instruments, in this two-part video series. Beginning with a hands-on demonstration of TI's Vision Library (VLIB) on a DaVinci DM6437 evaluation board, Jeff and Goksel touch upon various aspects of embedded vision engineering: algorithm design and prototyping in a PC environment, embedded software porting and optimization, and selection of a cost-effective hardware platform. Highlighting the need for embedded-friendly APIs, Goksel reports on his experiences with the performance speedups achievable through compiler options, loop unrolling, and C6x DSP intrinsics, and he points out available TI resources that enable vision developers to follow in his footsteps.

CEVA Demonstration of the Digital Video Stabilizer Module for the CEVA-MM3000 Platform
The CEVA Digital Video Stabilizer (DVS) is an advanced software application that is able to handle both shakiness and rolling shutter effects to output smoother video streams for embedded devices such as smartphone, tablets and others. Features supported include rolling shutter (Jello effect) and multiple axis correction, which reduce shakiness and smooth the motion when panning, zooming and rotating, in any light conditions.

More Videos

Vision-Based Automotive Safety Systems Go Mainstream
For most of my career, computer vision has been filed away in my mind as one of those cool technologies that was just too complex, expensive, and temperamental for me to use. But times change. Today we find computer vision integrated into a growing range of high-volume products, including game consoles, smartphones, and cars. I use the term "embedded vision" to refer to this proliferation of computer vision into embedded systems, mobile devices, PCs, and the cloud — creating "machines that see and understand." More

Can Demand Match Supply For Wireless In Mobile Video Surveillance?
A surplus supply of wireless download technology was fitted to 16 percent of all video recorders sold in mobile video surveillance markets during 2012, according a new report entitled “The World Market for Mobile Video Surveillance” from IMS Research, now part of IHS. This is technology that the customer either never intends to use, or doesn’t have the back-end software to support. So does this mean that manufacturers are wasting their money on oversupply? More

More Articles

Pedestrian Detection 8x Faster: Uses HOG

Graduate Student Seeks Expert Opinion

Big Challenge on Bitmap Comparison

More Community Discussions

Samsung and Android: Multiple Embedded Vision Platforms You Shouldn’t Avoid

Google Glass: A Teardown Analysis

Nokia's Lumia 1020: A Smartphone with Image Quality A-Plenty

More News