Embedded Vision Insights: November 10, 2015 Edition

Dear Colleague,

I'm delighted to tell you about three new videos published to the Alliance website. Basler begins with a tutorial on industrial camera interfaces; the different kinds and most common options available, followed by a practical design example. Synopsys focuses on ADAS; its video from the 2015 Embedded Vision Summit demonstrates a speed sign detection algorithm running on a FPGA-housed version of the company's neural-network-focused vision processor core. And speaking of FPGAs, Xilinx demonstrates in its Embedded Vision Summit video the company's new high-level SDSoC development environment, applicable to both Zynq-7000 and newest Zynq UltraScale CPU+FPGA chips.

There’s also plenty of new written content on the Alliance website. "Increasing Performance and Power Efficiency in Heterogeneous Software," the latest in a series of articles from Imagination Technologies, describes a typical use case for heterogeneous computing and the challenges (and their solutions) that result from moving to a heterogeneous programming model. Shorter writeups come from Auviz Systems, with a trip report on a recent Boston Image Processing Computer Vision Group meeting covering deep learning, and from Synopsys, on optimizing DSPs for vision-based automotive applications. And don't forget to also check out the market analysis and press release sections of the website, which contain several new entries.

Finally, speaking of the Embedded Vision Summit, I'd like to remind you of next year's event, taking place from May 2-4, 2016 in Santa Clara, California. Now in its fourth year, the inspiring and practical Embedded Vision Summit will focus exclusively on bringing visual intelligence to your products, whether embedded, wearable, cloud-based or mobile. New breakthroughs. New technology. New insights. And expanded offerings across the program. It’s an event you won’t want to miss. Mark your calendar and keep an eye on the website and this newsletter for more information to come shortly.

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. If you have an idea as to how the Alliance can better service your needs, please contact me.

Brian Dipert
Editor-In-Chief, Embedded Vision Alliance

"Vision-Based Gesture User Interfaces," a Presentation from Qualcomm
Francis MacDougall, Senior Director of Technology at Qualcomm, presents the "Vision-Based Gesture User Interfaces" tutorial within the "Vision Applications" technical session at the October 2013 Embedded Vision Summit East. MacDougall explains how gestures fit into the spectrum of advanced user interface options, compares and contrasts the various 2-D and 3-D technologies (vision and other) available to implement gesture interfaces, gives examples of the various gestures (and means of discerning them) currently in use by systems manufacturers, and forecasts how the gesture interface market may evolve in the future.

VectorBlox Demonstration of Various Vision Algorithms
Guy Lemieux, Founder and CEO of VectorBlox, demonstrates the company's latest embedded vision technologies and products at the May 2015 Embedded Vision Alliance Member Meeting. Specifically, Lemieux demonstrates various vision processing applications running on the company's MXP matrix processor.

More Videos

Computer Vision Metrics: Survey, Taxonomy, and Analysis
The Embedded Vision Alliance is pleased to provide you with a free electronic copy of this in-depth technical resource, with book chapters available on the Alliance website in both HTML and PDF formats. Computer Vision Metrics provides an extensive survey and analysis of over 100 current and historical feature description and machine vision methods, with a detailed taxonomy for local, regional and global features. The book provides the necessary background to develop intuition about why interest point detectors and feature descriptors actually work, as well as how they are designed, along with observations about tuning the methods for achieving robustness and invariance targets for specific applications. Also see the Alliance's interview with author Scott Krig, as well as Krig's Alliance Member Meeting presentation. More

Intruder Alarm Equipment: Where’s the Growth?
The U.S. market for intruder alarm equipment, which makes up 40 percent of the global market, reached $1.1 billion dollars last year. Numerous attempts have been made all over the world to replicate this success, ranging from home management to do-it-yourself (DIY) "bells and whistles" systems. This article from IHS analyst Jim Dearing provides an overview of the current state of the American market, highlighting a few bright spots for growth. More

More Articles

Xilinx Showcases Industry’s First 16nm All Programmable MPSoC at ARM TechCon 2015

TI Strengthens ADAS Portfolio with the Introduction of Latest Processor in TDA Family

ON Semiconductor Announces Sampling of Next Generation Automotive Image Sensor with LED Flicker Mitigation and ASIL B Support

Qualcomm Signs Definitive Agreement to Sell Vuforia Business to PTC

VATICS Chooses CEVA Imaging and Vision DSP for its Surveillance and Smart Camera SoCs

More News