Join the Khronos Group at the Embedded Vision Summit which is the only event focused exclusively on the hottest topic in the electronic industry today: deployable computer vision!

Bookmark this web page as your information hub to all that is Khronos at EVS this year.

Don’t miss this year’s OpenVX Workshop at Embedded Vision Summit. Khronos will present a day-long hands-on workshop all about OpenVX cross-platform neural network acceleration API for embedded vision applications. We’ve developed a new curriculum so even if you attended in past years, this is a do-not-miss, jam-packed tutorial with new information on computer vision algorithms for feature tracking and neural networks mapped to the graph API. We’ll be doing a hands-on practice session that gives participants a chance to solve real computer vision problems using OpenVX with the folks who created the API. We’ll also be talking about the OpenVX roadmap and what’s to come. 

Khronos OpenVX Workshop for Vision and Neural Network Acceleration

Location: Great America Meeting Room #1
Date: Wednesday, May 3rd 2017

OpenVX is a royalty-free open standard API released by the Khronos Group. OpenVX enables performance and power-optimized computer vision and machine learning functionality, especially important in embedded and real-time use cases. The course covers the graph API that enables OpenVX developers to efficiently run computer vision algorithms on heterogeneous computing architectures. A set of example algorithms for feature tracking and neural networks mapped to the graph API will be discussed. Also covered is the relationship between OpenVX and OpenCV, as well as OpenCL. The course includes hands-on practice session that gets the participants started on solving real computer vision problems using OpenVX.

Intended Audience: Engineers, researchers, and software developers who develop computer vision and machine learning applications and want to benefit from transparent hardware acceleration.

Register today

Time	Session	Speaker
09:00-09:15	OpenVX ecosystem overview	Frank Brill, Cadence
09:15-09:45	Introduction to OpenVX	Radha Giduthuri, AMD
09:45-10:30	Hands-on exercise#1 (objects, graphs, alexnet)	Tomer Schwartz, Intel
10:30-11:00	Morning break
11:30-11:45	Introduction to OpenVX SC	Jesse Villarreal, TI
11:45-12:30	Hands-on exercise#2 (export and deploy)	Thierry Lepley, Cadence
12:30-13:30	Lunch break
13:30-13:45	OpenVX roadmap	Frank Brill, Cadence
13:45-14:00	Introduction to NNEF	Peter McGuinness
14:00-15:00	Using SYCL with OpenVX ecosystem	Andrew Richards, Codeplay
15:00-15:30	Afternoon break
15:30-16:45	OpenVX implementor presentations	AMD, Cadence, Imagination, Intel, TI
16:45-17:00	Wrap-up and Q&A

Register today

 

Khronos Technology Related Sessions

Vision Acceleration API Landscape: Options and Trade-offs

Presentation by: Neil Trevett, President, Khronos | VP, NVIDIA
Date/Time: Monday, May 1, 2:00 PM - 2:30 PM

The landscape of APIs for accelerating vision and neural network software using specialized processors continues to rapidly evolve. Many industry-standard APIs, such as OpenCL and OpenVX, are being upgraded to increasingly focus on deep learning, and the industry is rapidly adopting the new generation of low-level, explicit GPU APIs, such as Vulkan, that tightly integrate graphics and compute. Some of these APIs, like OpenVX and OpenCV, are vision-specific, while others, like OpenCL and Vulkan, are general-purpose. Some, like CUDA and TensorRT, are vendor-specific, while others are open standards that any supplier can adopt. Which ones should you use for your project?

Frank Brill manages OpenVX software development for Cadence’s Tensilica Imaging and Vision DSP organization.  He started his career doing computer vision research and development for video surveillance applications at Texas Instruments, and then moved into silicon device program management, where he was responsible for several digital still camera and multimedia chips.  Since then, Frank has managed computer vision R&D groups at TI, NVIDIA, Samsung, and now at Cadence, and has represented all four companies in the Khronos OpenVX working group.  He joined Cadence in 2016 to work full-time on OpenVX, and currently serves as chairperson of the OpenVX working group.

Training CNNs for Efficient Inference

Presentation by: Paul Brasnett, Principal Research Engineer, Imagination Technologies
Date/Time: Tuesday, May 2, 11:15 AM - 11:45 AM

Imagination will showcase OpenVX with CNN extensions on PowerVR GPUs.

 

 

Khronos Members Speaking at EVS

Member Company	Presentation
Amazon	How Image Sensor and Video Compression Parameters Impact Vision Algorithms
ARM	Computer Vision on ARM: Faster Ways to Optimize Software for Advanced Mobile Computing Platforms
ARM	Executive Perspective Presentation: This Changes Everything — Why Computer Vision Will Be Everywhere
ARM	Computer Vision on ARM: The Spirit Object Detection Accelerator
Cadence	Scalable Neural Network Processors for Embedded Applications
Cadence	Techniques to Reduce Power Consumption in Embedded DNN Implementations
Ceva	Fast Inference in Low Power Systems via CEVA’s Deep Neural Network Solution
Elvees	Designing a Stereo IP Camera From Scratch
Google	Implementing the TensorFlow Deep Learning Framework on Qualcomm’s Low-power DSP
Google	The Rapid Evolution and Future of Machine Perception
IMGTEC	Training CNNs for Efficient Inference
Intel	The Battle Between Traditional Algorithms and Deep Learning: The 3 Year Horizon
Intel	Designing Deep Neural Network Algorithms for Embedded Devices
Intel	How Intel’s Latest RealSense Technology Can Help Your Embedded Systems See, Navigate, and Understand the Real World
Intel	Making OpenCV Code Run Fast
Intel	Executive Perspective Presentation: Vision for All?
Khronos	The OpenVX Computer Vision Library Standard for Portable, Efficient Code
Microsoft	Emotion Recognition From Images In the Wild
NVIDIA / Khronos	Vision Acceleration API Landscape: Options and Trade-offs
NXP	Choosing the Optimum Mix of Sensors for Driver Assistance and Autonomous Vehicles
NXP	Implementing an Optimized CNN Traffic Sign Recognition Solution
Panasonic	A Fast Object Detector for ADAS using Deep Learning
Qualcomm	Always-On Vision Becomes a Reality
Qualcomm	Computer Vision and Machine Learning at the Edge
Sony	Image Sensor Formats and Interfaces for IoT Applications
Synops	Designing Scalable Embedded Vision SoCs from Day 1
Videantis	Computer-vision-based 360-degree Video Systems: Architectures, Algorithms and Trade-offs
Xilinx	Caffe to Zynq: State-of-the-Art Machine Learning Inference Performance in Less Than 5 Watts
Xilinx	OpenCV on Zynq: Accelerating 4k60 Dense Optical Flow and Stereo Vision

Maps

Khronos Member Sponsors

Conference Code of Conduct: The Khronos Group is dedicated to providing a harassment-free conference experience for everyone. Visit our Code of Conduct page to learn more.