The October 2013 Embedded Vision Summit East

 

Engineers: Learn to Design Machines That See!
October 2, 2013
Westford Regency Inn and Conference Center
219 Littleton Road
Westford, MA 01886

On Wednesday, October 2, 2013 at the Westford Regency Inn and Conference Center in Westford, Massachusetts, in the Boston, Massachusetts area, the Embedded Vision Alliance hosted the Embedded Vision Summit East, a technical educational forum for engineers interested in incorporating visual intelligence into electronic systems and software.

For more information about the Embedded Vision Summit, please see below.

The October 2013 Embedded Vision Summit East is now concluded.


Day Two: Embedded Vision Hands-on Workshops

On Thursday October 3rd, 2013 from 8:30AM-1:30PM (including optional 1-hour complimentary lunch), Embedded Vision Alliance members Analog Devices, Avnet Electronics Marketing and BDTI co-presented a workshop exploring hardware and software for image processing and video analytics, featuring the Avnet/Analog Devices Embedded Vision Starter Kit. This workshop was an excellent starting point for vision application developers interested in exploring a wide range of embedded vision applications.

That same day, from 1:00PM-5:00PM, Alliance members Avnet Electronics Marketing and Xilinx co-presented a workshop introducing 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. An OpenCV example was used to demonstrate how a software implementation of an embedded vision application can be accelerated by building a custom hardware accelerator on the Zynq SoC’s programmable fabric, achieving 1080P60 at 1W power consumption.

Both workshops are now concluded. For more information on both workshops, please see the October 2013 Embedded Vision Summit East Workshops page.


Embedded Vision Summit Keynote: "Embedding Computer Vision in Everyday Life" by Mario E. Munich of iRobot

Mario E. Munich is Vice President of Advanced Development at iRobot in Pasadena, California, where he currently manages the research and advanced development efforts. He was formerly the CTO of Evolution Robotics, a company focused on development key technology primitives for consumer robotics. He received the degree of Electronic Engineer (with honors) from the National University of Rosario, Argentina, in 1990, and the M.S. and Ph.D. degrees in Electrical Engineering from the California Institute of Technology, Pasadena, in 1994 and 2000, respectively.  His PhD work focused in developing novel Human-Machine Interfaces using video technology and computer vision techniques. At Evolution Robotics, he worked in development of object recognition, mapping and navigation algorithms for consumer robotics. His research interests includes computer vision, autonomous navigation, and human-robotic interaction.

Embedded Vision Summit Special Presentation: "The DARPA Visual Media Reasoning Program" by Mike Geertsen of DARPA

Under the Visual Media Reasoning (VMR) program, DARPA has facilitated the development of a range of innovative computer vision technologies, all focused on a common question: can a meta-reasoning (i.e. "lightweight AI") system that fuses and reasons over the input of multiple "fragile" vision algorithms dramatically improve system performance? As part of this program, DARPA has created two general-purpose vision system development tools which DARPA and its contractors will make widely available. One of these tools enables the automated evaluation of vision algorithm performance over a massive parameter space. The other enables generation of synthetic image content for use in training and testing detection and recognition algorithms. These tools are planned to be released as an adjunct to the OpenCV open source computer vision software library in late 2013 or early 2014.

At the Embedded Vision Summit, Mike Geertsen, DARPA Program Manager, will present an overview of the VMR program and the enabling tools developed under it. He joined DARPA as a Program Manager in 2011 and brings over 25 years of experience in private sector technology innovation. His areas of technical interest include geospatial, simulation and mobile technologies. He brings to DARPA a passion for increasing the speed at which the warfighter can benefit from emerging commercial technologies and small business innovation. He joined DARPA from his role as President of Depiction Inc., a software start-up he co-founded. Earlier in his career he held a variety of positions with Microsoft, including new product development in their simulation games group.

For more information on the presentations by DARPA's contractors, please see the abstracts for the talks from Next Century Corporation and SRI International.

Information on the technical presentation speakers can be found here. Abstracts for select technical presentations can be found here.

Event Agenda

Below you'll find an overview of the agenda for the October 2013 Embedded Vision Summit East.

8:00-9:00AM: Registration

9:00-9:30AM: Welcome remarks and program overview, by Jeff Bier, Embedded Vision Alliance

9:30-10:30AM: Keynote presentation "Embedding Computer Vision in Everyday Life" by Mario E. Munich, iRobot

10:30-11:00AM: Morning Break with Demos

Track 1: Fundamentals

Session 1A: Vision Applications

11:00-11:30AM: "What Can You Do With Embedded Vision?" by Jeff Bier, Embedded Vision Alliance

11:30AM-12:00PM: "Vision-Based Gesture User Interfaces" by Francis MacDougall, Qualcomm

12:00-12:30PM: "Vision-Based Automotive Driver Assistance Systems: Challenges and Approaches" by Paul Zoratti, Xilinx

Track 2: Advanced Topics

Session 2A: Algorithm Development Techniques and Tools

11:00-11:30AM: "The DARPA Visual Media Reasoning Program" by Mike Geertsen, DARPA

11:30AM-12:00PM: "Using Synthetic Image Generation to Reduce the Cost of Vision Algorithm Development" by Clark Dorman, Next Century Corporation

12:00-12:30PM: "Tools for 'Democratizing' Computer Vision" by Jayan Eledath, SRI International

12:30-1:30PM: Lunch with Demos

Session 1B: Object and Feature Detection

1:30-2:00PM: "Finding Objects Using Canny Edge Detection" by Eric Gregori, BDTI

2:00-2:30PM: "Algorithms for Object Detection and Tracking" by Tim Jones, MathWorks

2:30-3:00PM: "Feature Detection: How It Works, When to Use It, and a Sample Implementation" by Marco Jacobs, videantis

Session 2B: Algorithms and Implementations

1:30-2:00PM: "Embedded Lucas-Kanade Tracking: How it Works, How to Implement It, and How to Use It" by Goksel Dedeoglu, Texas Instruments

2:00-2:30PM: "Porting Applications to High-Performance Imaging DSPs" by Gary Brown, Cadence (Tensilica)

2:30-3:00PM: "Designing a Multi-Core Architecture Tailored for Pedestrian Detection Algorithms" by Tom Michiels, Synopsys

3:00-3:30PM: Afternoon Break with Demos

Session 1C: Implementing Vision Systems

3:30-4:00PM: "Targeting Computer Vision Algorithms to Embedded Hardware" by Mario Bergeron, Avnet Electronics Marketing

4:00-4:30PM: "Using FPGAs to Accelerate 3D Vision Processing: A System Developer’s View" by Ken Lee, VanGogh Imaging

4:30-5:00PM: "Using Heterogeneous Computing for Mobile and Embedded Vision" by Rick Maule, Qualcomm

5:00-5:30PM: "Embedded 3D Stereo Vision: How it Works, How to Implement It, and How to Use It" by Goksel Dedeoglu, Texas Instruments

Session 2C: Front-End Image Processing for Vision Applications

3:30-4:00PM: "Better Image Understanding Through Better Sensor Understanding" by Michael Tusch, Apical

4:00-4:30PM: "Efficient Super-Resolution Algorithms and Implementation Techniques for Constrained  Applications" by Ilan Yona, CEVA

4:30-5:00PM: "Efficiently Computing Disparity Maps for Low-Cost 3D Stereo Vision" by Tom Wilson, CogniVue

5:00-5:30PM: "Implementing Real-Time Hyperspectral Imaging" by Kalyanramu Vemishetty, National Instruments

5:30-7:30PM: Reception with Demos

A Great Event for System, Software and Chip Design Engineers

The Embedded Vision Summit provides a technical educational forum for engineers, including how-to presentations, seminars, demonstrations, and opportunities to interact with Alliance member companies. This event is intended to:

  • Inspire engineers' imaginations about the potential applications for embedded vision technology through exciting presentations and demonstrations.
  • Offer practical know-how for engineers to help you incorporate vision capabilities into your products.
  • Provide opportunities for engineers to meet and talk with leading embedded vision technology companies and learn about their offerings.

See here for a video that summarizes attendee and Alliance member company representative impressions of the April 2013 Embedded Vision Summit, held in San Jose, California.

Press and Analysts Welcome

For business and technology publication editors, market researchers, and financial analysts, the Summit provides unique insights into the business and technology drivers behind the rapid proliferation of embedded vision – “machines that see” – in virtually every category of electronic products, from automobiles to consumer electronics to health care. The Summit will provide a concentrated opportunity to hear from and interact with embedded vision leaders from industry and academia, and will culminate in a series of live demonstrations of new embedded vision products and technologies.

Alliance Membership and Summit Sponsorship

Founded in 2011 and led by BDTI, the Alliance is an industry collaboration to transform the electronics industry with products that are more intelligent and aware of their environments. It is a membership-based entity dedicated to inspiring and empowering embedded system designers to use embedded vision technology. A key means of achieving this is providing design engineers with the practical information that they need in order to effectively incorporate embedded vision technology in their designs.

The Embedded Vision Summit is an Alliance Member-funded event which enables Alliance Member companies to highlight their leadership in embedded vision and capture the attention of design engineers, press and analysts interested in embedded vision. The Alliance offers sponsorship and other marketing opportunities to companies leading the embedded vision revolution.

Embedded Vision Summit Sponsors

Premier

Qualcomm  

Gold

Analog Devices BDTI
   
Synopsys Xilinx

Silver

Avnet  

Conference Collateral

videantis  

Product Demonstrations

The following Embedded Vision Alliance member companies offered product demonstrations during the morning and afternoon breaks, at lunch, and during the evening reception:

  • Analog Devices
  • Apical
  • ARM
  • Avnet
  • BDTI
  • Bluetechnix
  • CEVA
  • CogniVue
  • Inrevium by Tokyo Electron Device
  • MathWorks
  • Qualcomm
  • Synopsys
  • Tensilica
  • Texas Instruments
  • videantis
  • Xilinx

If you have other questions about the Embedded Vision Summit, please contact us at summit@embedded-vision.com.