Video Interviews & Demos

Vinay Singh, Senior Product Marketing Manager at Xilinx, demonstrates a motion detection application running on the company's Zynq-7000 All Programmable SoC at the April 2013 Embedded Vision Summit.

For more information about Xilinx, please send the company an email or visit the company's website.

Paul Zoratti, Automotive Driver Assistance System Architect at Xilinx, demonstrates an ADAS application running on the company's Zynq-7000 All Programmable SoC at the April 2013 Embedded Vision Summit.

For more information about Xilinx, please send the company an email or visit the company's website.

Tim Jones, principal application engineer at MathWorks, presents the "Algorithms for Object Detection and Tracking" tutorial within the "Using Vision Algorithms" technical session at the April 2013 Embedded Vision Summit.

José Alvarez, Engineering Director for Video Technology at Xilinx, presents the "Challenges and Opportunities in Accelerating OpenCV" tutorial within the "Developing Vision Software, Accelerators and Systems" technical session at the April 2013 Embedded Vision Summit. Computer vision continues to see increased adoption across a wide variety of applications. The industry's trend towards the incorporation of Smarter Vision capabilities is driving the need for ever more intelligent algorithms that are capable of image understanding.

In this demonstration, you'll see the power of the CEVA DSP platform and gesture recognition technology from partner and fellow Embedded Vision Alliance member eyeSight. The CEVA-plus-eyeSight solution supports multiple hand gestures as well as palm detection and tracking, handles multiple users, works up to 4.5 meters away from the device, and operates in low light conditions.

In this demonstration, the power and flexibility of the CEVA-MM3101 is shown enabling an advanced face recognition capability, which could be implemented for video conferencing, gaming social networking or automotive applications. A simple HDMI connection between the video input device -- a handheld video camera, for example -- and the CEVA-based board is all that is required.

Adar Paz, Imaging and Computer Vision Team Leader at CEVA, presents the "Using Advanced Algorithms to Bring Vision Capabilities to Power-Constrained Devices" tutorial within the "Using Vision Algorithms" technical session at the April 2013 Embedded Vision Summit.

Mario Bergeron, Technical Marketing Engineer at Avnet Electronics, presents the "Targeting Computer Vision Algorithms to Embedded Hardware" tutorial within the "Developing Vision Software, Accelerators and Systems" technical session at the April 2013 Embedded Vision Summit. This presentation explores how computer vision algorithms can be targeted to embedded hardware, including FPGAs.

Eric Gregori, senior software engineer and embedded vision specialist at BDTI, presents the "Finding Objects Using Canny Edge Detection" tutorial within the "Using Vision Algorithms" technical session at the April 2013 Embedded Vision Summit. This presentation dives into the Canny edge detection algorithm; how it works and how to use it. Topics include a Canny algorithm walk through, connecting edges with contours, and classifying contours with mathematical models. Finally, the topics learned are applied to describe a system for counting dots on dice.

Marc Duruy, EMEA Sales Manager at Aldebaran Robotics, demonstrates the company's latest embedded vision technologies and products in partner (and Embedded Vision Alliance member) MathWorks' booth at the February 2013 Embedded World Conference.

Lorenz Kolb, Member of the Technical Staff at Missing Link Electronics (MLE), demonstrates the company's latest embedded vision technologies and products in partner (and Embedded Vision Alliance member) Xilinx's booth at the February 2013 Embedded World Conference.

For more information about Xilinx, please send the company an email or visit the company's website.

Adel Ghazel, R&D Program Manager at EBSYS (Embedded systems Technology), demonstrates the company's latest embedded vision technologies and products in partner (and Embedded Vision Alliance member) Analog Device's booth at the February 2013 Embedded World Conference.

For more information about Analog Devices, please send the company an email or visit the company's website.

Bo Wu, Technical Marketing Manager at Synopsys, presents the "Optimization and Acceleration for OpenCV-Based Embedded Vision Applications" tutorial within the "Using Tools, APIs and Design Techniques for Embedded Vision" technical session at the September 2012 Embedded Vision Summit.

Reach beyond the lens with Balwinder Kaur and Joe Rickson of Aptina Imaging as they break down Android's camera stack for the San Francisco Android User Group on August 28, 2012, including what's new and changed in "Jelly Bean" (Android 4.1).

Ms. Kaur covers camera APIs and their functions inside Android. Mr. Rickson then discusses the hardware application layers beneath it all. Dig as deep into the Android camera stack as you want in this two-for-one presentation.

Attendees at the 2012 HOT CHIPS symposium recently learned about Analog Devices’ new BF60x family of video and vision processors and their associated capabilities. Robert Bushey, principal architect and technologist, Embedded Systems Products and Technology Business Unit, presented about the BF60x family at the gathering, which is one of the semiconductor industry’s leading conferences on high-performance microprocessors and related integrated circuits.

Jeff Bier, founder of the Embedded Vision Alliance, interviews Daniel Wilding, National Instruments Digital Hardware Engineer. Jeff and Daniel discuss National Instruments' history, current status and future plans in the embedded vision application space, the applicability and advantages of FPGAs as embedded vision processors, and National Instruments' development tools for simplifying and otherwise optimizing FPGA-based embedded vision designs.

IMS Research senior analyst John Morse delivers an embedded vision application market trends presentation at the December 2012 Embedded Vision Alliance Member Summit. John analyzes the potential fit for a transition to embedded vision in various historical computer-based machine vision applications, spanning established, developing and emerging markets. He discusses both opportunities and barriers to entry in each application, as well as quantifying the potential market size and growth over time.

Mark Kulaczewski, Co-Founder and Vice President of System Integration at videantis, demonstrates the company's latest embedded vision technologies and products at the December 2012 Embedded Vision Alliance Member Summit.

Ken Lee, Founder and CEO at VanGogh Imaging, demonstrates the company's latest embedded vision technologies and products at the September 2012 Embedded Vision Summit.

For more information about VanGogh Imaging, please send the company an email or visit the company's website.

Kamalina Srikant, Product Marketing Manager at National Instruments, demonstrates the company's latest embedded vision technologies and products at the September 2012 Embedded Vision Summit.

Gabby Yi, DSP Applications Engineer at Analog Devices, demonstrates the company's latest embedded vision technologies and products at the September 2012 Embedded Vision Summit.

For more information about Analog Devices, please send the company an email or visit the company's website.

Jeff Bier, Embedded Vision Alliance Founder, moderates a discussion panel comprised of the presenters in the "Embedded Vision Applications and Algorithms" technical session at the September 2012 Embedded Vision Summit; Mario Bergeron from Avnet, Simon Morris from CogniVue, and Bo Wu from Synopsys.

Ken Lee, CEO at VanGogh Imaging, presents the "Challenges and Techniques in Using CPUs and GPUs for Embedded Vision" tutorial within the "Using Processors for Embedded Vision" technical session at the September 2012 Embedded Vision Summit. Topics discussed in the presentation include the unique challenges posed by mobile vision processing and how a hybrid combination of CPU, GPU and FPGA hardware is required to meet the challenge.

Jeff Bier, Embedded Vision Alliance Founder, moderates a discussion panel comprised of the presenters in the "Embedded Vision Applications and Algorithms" technical session at the September 2012 Embedded Vision Summit; Gabby Yi from Analog Devices, Michael Fawcett from iVeia, and Goksel Dedeoglu from Texas Instruments.

Mario Bergeron, Technical Marketing Engineer at Avnet Electronics Marketing, presents the "Addressing System Design Challenges in Embedded Vision" tutorial within the "Using Tools, APIs and Design Techniques for Embedded Vision" technical session at the September 2012 Embedded Vision Summit. Embedded vision applications need to move video data from the image sensor to processing and storage elements. When dealing with higher video resolutions and/or frame rates, this fact presents design challenges that need to be thought out early in the architecture phase.

Michael Tusch, founder and CEO of Apical, presents the "Harnessing Hardware Accelerators to Move from Algorithms to Embedded Vision" tutorial within the "Using Processors for Embedded Vision" technical session at the September 2012 Embedded Vision Summit. The presentation focuses on the programming challenges associated with implementing vision algorithms efficiently on embedded devices with a degree of hardware parallelization. Tusch illustrates the two fundamental issues of data flow and memory access with simple code examples.

Goksel Dedeoglu, Manager of the Embedded Vision Team at Texas Instruments' Systems and Applications R&D Center, presents the "Moving Object Segmentation for Security and Surveillance Applications" tutorial, part of the "Embedded Vision Applications and Algorithms" technical session at the September 2012 Embedded Vision Summit. Goksel’s presentation defines the purpose and uses of MOS (moving object segmentation) functions.

As the needs of businesses, governments and financial institutions drive new uses for video surveillance systems, there is a growing demand for increased analytics and more "vision" and intelligence in the end equipment. This evolution is pushing the need for additional processing power; the type of performance offered by multicore processors. This Ask the Expert video from Texas Instruments briefly explains how multicore DSPs are well suited to meet the processing and analytics needs of video surveillance equipment.

Jeff Bier, Founder of the Embedded Vision Alliance and co-founder and president of BDTI, presents the day-opening "Introduction to Embedded Vision" tutorial at the September 2012 Embedded Vision Summit. Topics discussed by Bier in his presentation include a technology overview, application examples, hardware, software and development tool trends, and an overview of the Embedded Vision Alliance.

Professor Rosalind Picard presents the morning keynote at the September 2012 Embedded Vision Summit. Professor Picard is the founder and director of the Affective Computing Research Group at the MIT Media Laboratory, co-director of the Things That Think Consortium (the largest industrial sponsorship organization at the lab) and leader of the new and growing Autism & Communication Technology Initiative at MIT. She is also co-founder, chief scientist and chairman of Affectiva, Inc., making technology to help measure and communicate emotion.

OpenCL is an emerging SDK (software development kit) that targets the problem of developing on heterogeneous multi-core platforms. Previously confined purely to the world of GPGPU (general-purpose computing on graphics processor units), it has recently also achieved acceptance on other hardware platforms, including fixed-function accelerators and even FPGAs.

Mark Kulaczewski, co-founder and Vice President of System Integration, demonstrates how the company's IP cores can optimize H.264 video compression efficiency and quality by identifying faces and other important information within each frame whose details must be preserved, at the July 2012 Embedded Vision Alliance Member Summit.

Bruce McCormick, Co-Founder, President and CEO, and Matt McCormick, Applications Development, use a Microsoft Kinect-based finger gesture recognition demonstration to showcase the capabilities of the company's CM1K neural network processor, at the July 2012 Embedded Vision Alliance Member Summit.

Xilinx's Video Scaler/OSD (on-screen display) reference designs allow the user to quickly evaluation and experiment with the Xilinx Video Scaler IP core. These reference designs work "out of the box" with the Avnet Spartan-6 Industrial Video Processing Kit (IVK). To learn more, visit Avnet's Design Resource Center.

Noman Hashim, Vice President of Sales, America and Europe, demonstrates Apical's latest embedded vision technologies and products at the March 2012 Embedded Vision Alliance Summit.

For more information about Apical, please send the company an email or visit the company's website.

Vineet Aggarwal, Group Manager for Embedded Systems, demonstrates National Instruments' latest embedded vision technologies and products at the March 2012 Embedded Vision Alliance Summit.

Navanee Sundaramoorthy, Product Manager for Processing Platforms, demonstrates Xilinx's latest embedded vision technologies and products at the March 2012 Embedded Vision Alliance Summit.

For more information about Xilinx, please send the company an email or visit the company's website.

Shaheen Kazin, Vice President of Marketing, demonstrates Omek Interactive's latest embedded vision technologies and products at the March 2012 Embedded Vision Alliance Summit.

Rear view camera image processing is one of the key emerging capabilities of advanced driver assistance and safety systems. In this demonstration by Goksel Dedeoglu, manager of TI’s Vision R&D, images captured by a rear view camera are fed to a 500 MHz DM6437 (TMS320DM6437) EVM.

Traffic sign recognition is one of emerging capabilities of advanced driver assistance and safety systems. In this demonstration, images captured by a 30 fps color camera are fed to algorithms running on a DM6437 EVM board and analyzed to detect circular traffic signs. When red circles are detected, they are further analyzed and classified within the set of European speed-limit signs.

This version of the video contains an English language soundtrack. For a Chinese language version of the video, please see:

The fingerprint recognition demonstration provided in the TMS320C6748 DSP Sys/BIOS software development kit offers a starting point for developing and demonstrating the real-time intelligence of TI's C674x DSPs.

CogniVue's motion detection and tracking demonstration shows how an individual's motion is identified and tracked. This basic demonstration software runs on the CV220X Image Cognition Processor, a low power, 9x9mm² SoC designed specifically for image processing and pattern detection/recognition functions, useful in a variety of computer vision applications.

CogniVue's collision avoidance system demonstration uses the CV220X Image Cognition Processor to detect and track a vehicle's lane as well as detect and track an obstacle vehicle in the path of the host vehicle. An alarm indicator signals when the obstacle vehicle comes within a warning threshold distance. The CV220X offers the best performance, per area, per power for driver assist system applications, and the CV2201 is offered in a 9x9 mm² package with a power consumption of under 250mW.

This example game is being played using only hand gestures, by means of a Microsoft Kinect paired with a CogniMem Technologies CM1K neural network processor. The extended multi-level play is suggestive of the robustness of the implementation. No modifications were made either to the game itself or to the Kinect peripheral.

For more, see this video in the Embedded Vision Academy.

This demonstration, which pairs a Freescale i.MX Quick Start board and CogniMem Technologies CM1K evaluation module, showcases how to use your eyes (specifically where you are looking at any particular point in time) as a mouse. Translating where a customer is looking to actions on a screen, and using gaze tracking to electronically control objects being showcased behind a transparent display such as Samsung’s, can result in a wide range of new applications for gamers, consumers, digital displays, and shop owners alike.

Apical's Noman Hashim, Vice President of Sales for America and Europe, presents the latest embedded vision news regarding the company's products at the March 2012 Embedded Vision Alliance Summit.

Texas Instruments' Brian Carlson, Senior Technology Strategist in the Wireless OMAP Business Unit, presents the latest embedded vision news regarding the company's products at the March 2012 Embedded Vision Alliance Summit.

IMS Research senior analyst Tom Hackenberg delivers an embedded vision application market trends presentation at the late-March 2012 Embedded Vision Alliance Summit. Tom analyzes the potential fit for embedded vision in a plethora of applications, spanning established, developing and emerging markets. He discusses both opportunities and barriers to entry in each application, as well as quantifying the potential market size and growth over time.

BDTI Senior Engineers Eric Gregori and Shehrzad Qureshi deliver a techology trends presentation on image sensors for embedded vision applications, at the late-March 2012 Embedded Vision Alliance Summit. Eric and Shehrzad discuss trends regarding conventional 2-D image sensors, as well as those supporting "3-D" (depth discernment) and "4-D" (i.e. selective focus, otherwise known as light field or plenoptic) functions.

Jim Donlon, Program Manager for DARPA (the U.S. Defense Advanced Research Projects Agency) describes the objectives, to-date history, current status and future plans of the Mind's Eye program. Mind's Eye "seeks to develop the capability for visual intelligence by automating the ability to learn generally applicable and generative representations of action between objects in a scene directly from visual inputs, and then reason over those learned representations.

Rapidly emerging applications in the area of embedded vision require ability to do real-time processing of one or more streams of HD video at high frame rates. In this demonstration, Xilinx's Navanee Sundaramoorthy, Product Manager for Processing Platforms, shows how you can use the Zynq-7000 Extensible Processing Platform with dual ARM Cortex-A9 processors and programmable logic for such applications. The programmable logic in the Zynq Z7020 brings 1080p60 video in and out of the device, as well as doing high data rate video processing.

This video describes the new ADSP-BF60x series of high-performance Blackfin Processors.  The BF608 and 609 are optimized for embedded vision applications and the BF606 and 607 are optimized for high-performance general purpose DSP applications.

Watch as TI's Laurent Le Gal demonstrates an application by ecosystem partner Scalado that enables users to "remove" objects from pictures taken with their phones or tablets, right on the device, to create a perfect shot.

Watch as TI's Laurent Le Gal demonstrates OMAP platform-empowered 360-panorama imaging capabilities on a phone, in partnership with scalado.

Try on and shop for the latest accessories - without ever leaving home. This demonstration of an augmented reality mirror uses face detection and tracking to give you a realistic preview of how accessories like Ray-Ban glasses will look before you buy. This demonstration is empowered by TI's OMAP processor and partner Total Immersion.

Brian Dipert, Editor-In-Chief of the Embedded Vision Alliance, interviews Jon Cropley, Principal Analyst at IMS Research, on February 28, 2012. In this introductory video to a planned series, Brian and Jon discuss (among other things) the applications for embedded vision in security and business intelligence applications, the varying locations for analytics intelligence in a system (within the camera, the server, both, etc), sizes of both the overall markets and subsets, and various market trends.

Watch as TI's Biju Pillai shows advanced imaging applications, including video stabilization, enhanced by the OMAP(tm) platform's imaging hardware accelerators to deliver great pictures with low power consumption.

Brian Dipert, Editor-In-Chief of the Embedded Vision Alliance, interviews Gene Frantz, Texas Instruments Principal Fellow. Gene, who has been with the company for nearly 40 years, did his early work with DSPs in association with the Speak & Spell speech synthesizer.

Machine vision is a branch of computer vision which is used in industries for the analysis of objects by capturing images and performing real time analysis. Major machine vision applications exist in quality control for the semiconductor industry and consumer products industry. Vision system controllers, smart cameras and frame grabbers capture live images and helps in identifying defective semiconductors and products. Machine vision applications require highly integrated system solutions which can provide compact, low cost, low power and high performance capabilities.

eyeSight Mobile Technologies' CTO Itay Katz demonstrates the company's gesture interface technologies to Embedded Vision Alliance Founder Jeff Bier at the 2012 Consumer Electronics Show. The demonstrations took place at CEVA's suite at CES. For more information, see Embedded Vision Alliance Editor-In-Chief Brian Dipert's writeup.

STMicroelectronics' Juan Hurtado demonstrates the company's natural user interface technologies to Embedded Vision Alliance Founder Jeff Bier at the 2012 Consumer Electronics Show.

Bodymetrics demonstrates its PrimeSense-based virtual clothes shopping system to Embedded Vision Alliance Founder Jeff Bier at the 2012 Consumer Electronics Show. For more information, see Embedded Vision Alliance Editor-In-Chief Brian Dipert's writeup.

Brian Dipert, Editor-In-Chief of the Embedded Vision Alliance, interviews Jeremiah Golston, Texas Instruments Fellow and Chief Architect of the company's DaVinci product line. They discuss Jeremiah's background in video (generally) and embedded vision (specifically), how the company's product line (guided by Jeremiah's architecture definition work) has evolved over the years in response to the needs of various imaging applications, and how it meets (and will further evolve to meet) the needs of various embedded vision applications both now and in the future.

Gary Bradski is the creator of OpenCV, the open-source library for computer vision. Our conversation with Gary discusses his latest work on robotics at Willow Garage.

By José Alvarez
Video Technology Engineering Director
Xilinx Corporation

This BDTI project evaluated high-level synthesis tools that use C code (or other high-level languages) to generate FPGA designs. As part of the tool evaluation, BDTI implemented an optical flow algorithm operating on high-definition video using a sub-$30 FPGA.

For more information about BDTI, please send the company an email or visit the company's website.

Jeff Bier, Founder of the Embedded Vision Alliance, interviews Jitendra Malik, Arthur J. Chick Professor of EECS at the University of California at Berkeley, on August 17, 2011. This is part two of a three-part video series. Please click here for part three.

Jeff Bier, Founder of the Embedded Vision Alliance, interviews Jitendra Malik, Arthur J. Chick Professor of EECS at the University of California at Berkeley, on August 17, 2011. This is the final part three of a three-part video series.

Jeff Bier, Founder of the Embedded Vision Alliance, interviews Goksel Dedeoglu, Texas Instruments Member of the Technical Staff in Vision R&D. Goksel, who began his career in vision technology as a university researcher (including earning a Ph.D. from Carnegie Mellon University), explains some of the key trade-offs faced by TI in creating its "VLIB" vision software component library. Jeff and Goksel also explore challenges and best practices for embedded vision system development.

Jeff Bier, Founder of the Embedded Vision Alliance, interviews Michael Tusch, Apical Limited Founder and CEO, on September 21, 2011.

For more information about Apical, please send the company an email or visit the company's website.

Jeff Bier takes to the streets to show the EVA community that BDTI is living the embedded vision lifestyle with a demonstration of the Mobileye system in his wife’s vehicle.

For more information about BDTI, please send the company an email or visit the company's website.

Vin Ratford describes the future of Embedded Vision.

For more information about Xilinx, please send the company an email or visit the company's website.

Hear Joe Mallett discuss Xilinx current platforms for embedded vision and the opportunities for expansion.

For more information about Xilinx, please send the company an email or visit the company's website.