May 2018 Embedded Vision Summit Replay

Please bookmark and revisit this page regularly, as new content is being published on an ongoing basis.

Conference Presentation Slides

2018 Embedded Vision Summit Slides
(249 MB—click to download.)

Conference Overview Presentations

Welcome Remarks and Conference Overview (Day 1)
Jeff Bier, Embedded Vision Alliance

Welcome Remarks and Conference Overview (Day 2)
Jeff Bier, Embedded Vision Alliance

Keynote Presentations

"Think Like an Amateur, Do As an Expert: Lessons from a Career in Computer Vision"
Dr. Takeo Kanade, Carnegie Mellon University

Business Insights Track Presentations

"Building Up a Start-up in Embedded Vision: Lessons from Machine Vision"
Arndt Bake, Basler

"Leveraging Cloud Computer Vision for a Real-time Consumer Product"
Pavan Kumar, Cocoon Cam

"The Four Key Trends Driving the Proliferation of Visual Perception"
Jeff Bier, Embedded Vision Alliance and BDTI

"Overcoming Bias in Computer Vision - A Business Imperative"
Will Byrne, Entrepreneur

"Data-driven Business Models Enabled by 3D Vision Technology"
Christopher Scheubel, FRAMOS

"Embedded AI for Smart Cities and Retail in China"
Yufeng Zhang, Horizon Robotics

"Using Vision to Transform Retail"
Sumit Gupta, IBM

"Balancing Safety, Convenience and Privacy in the Era of Ubiquitous Cameras"
Charlotte Dryden, Intel

"Intelligent Consumer Robots Powering the Smart Home"
Mario Munich, iRobot

"Computer Vision for Industrial Inspection: From PCs to Embedded"
Thomas Däubler, NET GmbH

"Reduce Risk in Computer Vision Design: Focus on the User"
Paul Duckworth, Twisthink

"What's Hot? The M&A and Funding Landscape for Machine Vision Companies"
Rudy Burger, Woodside Capital Partners

"Leveraging Edge and Cloud for Visual Intelligence Solutions"
Salil Raje, Xilinx

"From 2D to 3D: How Depth Sensing Will Shape the Future of Vision"
Guillaume Girardin, Yole Développement

Vision Entrepreneurs' Panel

Vision Tank Competition Finalist Presentations
AiFi, Aquifi, Boulder AI, Sturfee and VirtuSense Technologies

Enabling Technologies Track Presentations

"A New Generation of Camera Modules: A Novel Approach and Its Benefits for Embedded Systems"
Paul Maria Zalewski, Allied Vision Technologies

"Deep Learning on Arm Cortex-M Microcontrollers"
Vikas Chandra, Arm

"Project Trillium: A New Suite of Machine Learning IP from Arm"
Steve Steele, Arm

"Neural Network Compiler: Enabling Rapid Deployment of DNNs on Low-Cost, Low-Power Processors"
Megha Daga, Cadence

"Rapid Development of Efficient Vision Applications Using the Halide Language and CEVA Processors"
Yair Siegel, CEVA, and Gary Gitelson, mPerpetuo

"New Memory-centric Architecture Needed for AI"
Sylvain Dubois, Crossbar

"The Journey and Sunrise Processors: Leading-Edge Performance for Embedded AI"
Kai Yu, Horizon Robotics

"Enabling Software Developers to Harness FPGA Compute Accelerators"
Bernhard Friebe, Intel

"Enabling Cross-platform Deep Learning Applications with the Intel CV SDK"
Yury Gorbachev, Intel

"Rethinking Deep Learning: Neural Compute Stick"
Ashish Pai, Intel

"Programmable CNN Acceleration in Under 1 Watt"
Gordon Hands, Lattice Semiconductor

"Machine Learning Inference In Under 5 mW with a Binarized Neural Network on an FPGA"
Abdullah Raouf, Lattice Semiconductor

"Deep Learning in MATLAB: From Concept to Optimized Embedded Code"
Avinash Nehemiah and Girish Venkataramani, MathWorks

"Infusing Visual Understanding in Cloud and Edge Solutions Using State Of-the-Art Microsoft Algorithms"
Anirudh Koul and Jin Yamamoto, Microsoft

"Mythic's Analog Deep Learning Accelerator Chip: High Performance Inference"
Frederick Soo, Mythic

"NovuTensor: Hardware Acceleration of Deep Convolutional Neural Networks for AI"
Mike Li, NovuMind

"Energy-efficient Processors Enable the Era of Intelligent Devices"
Ren Wu, NovuMind

"Pilot AI Vision Framework: From Doorbells to Defense"
Jonathan Su, Pilot AI

"Achieving High-Performance Vision Processing for Embedded Applications with Qualcomm SoC Platforms"
Sahil Bansal, Qualcomm

"Designing Smarter, Safer Cars with Embedded Vision Using EV Processor Cores"
Fergus Casey, Synopsys

"A Physics-based Approach to Removing Shadows and Shading in Real Time"
Bruce Maxwell, Tandent Vision Science

"Optimizing Your System Software and BSP for Embedded Vision and AI"
Daniel Sun, Thundersoft

"Achieving 15 TOPS/s Equivalent Performance in Less Than 10 W Using Neural Network Pruning on Xilinx Zynq"
Nick Ni, Xilinx

"Exploiting Reduced Precision for Machine Learning on FPGAs"
Kees Vissers, Xilinx

"High-end Multi-camera Technology, Applications and Examples"
Max Larin, XIMEA

"At the Edge of AI At the Edge: Ultra-efficient AI on Low-power Compute Platforms"
Mohammad Rastegari, XNOR.ai

"Embedding Programmable DNNs in Low-Power SoCs"
Steve Teig, Xperi

Fundamentals Track Presentations

"Bad Data, Bad Network, or: How to Create the Right Dataset for Your Application"
Mike Schmit, Advanced Micro Devices (AMD)

"Depth Cameras: A State-of-the-Art Overview"
Carlo Dal Mutto, Aquifi

"Designing Vision Front Ends for Embedded Systems"
Friedrich Dierks, Basler

"Introduction to LiDAR for Machine Perception"
Mohammed Musa, Deepen AI

"Introduction to Optics for Embedded Vision"
Jessica Gehlhar, Edmund Optics

"Solving Vision Tasks Using Deep Learning: An Introduction"
Pete Warden, Google

"Introduction to Creating a Vision Solution in the Cloud"
Nishita Sant, GumGum

"Visual-Inertial Tracking for AR and VR"
Timo Ahonen, Meta

"Approaches for Energy Efficient Implementation of Deep Neural Networks"
Vivienne Sze, MIT

"Understanding Automotive Radar: Present and Future"
Arunesh Roy, NXP Semiconductors

"Understanding and Implementing Face Landmark Detection and Tracking"
Jayachandra Dakala, PathPartner Technology

"From Feature Engineering to Network Engineering"
Auro Tripathy, ShatterLine Labs (representing AMD)

"Optimize Performance: Start Your Algorithm Development With the Imaging Subsystem"
Ryan Johnson, Twisthink

"Building A Practical Face Recognition System Using Cloud APIs"
Chris Adzima, Washington County Sheriff’s Office, Oregon

Technical Insights Track Presentations

"The OpenVX Computer Vision and Neural Network Inference Library Standard for Portable, Efficient Code"
Radhakrishna Giduthuri, Advanced Micro Devices (AMD)

"How Simulation Accelerates Development of Self-Driving Technology"
László Kishonti, AImotive

"Understanding Real-World Imaging Challenges for ADAS and Autonomous Vision Systems – IEEE P2020"
Felix Heide, Algolux

"Generative Sensing: Reliable Recognition from Unreliable Sensor Data"
Professor Lina Karam, Arizona State University

"Even Faster CNNs: Exploring the New Class of Winograd Algorithms"
Gian Marco Iodice, Arm

"Deploying CNN-based Vision Solutions on a $3 Microcontroller"
Greg Lytle, Au-Zone Technologies

"Harnessing the Edge and the Cloud Together for Visual AI"
Sébastien Taylor, Au-Zone Technologies

"Computer Vision Hardware Acceleration for Driver Assistance"
Markus Tremmel, Bosch

"The Perspective Transform in Embedded Vision"
Shrinivas Gadkari and Aditya Joshi, Cadence

"Programming Techniques for Implementing Inference Software Efficiently"
Andrew Richards, Codeplay Software

"Architecting a Smart Home Monitoring System with Millions of Cameras"
Hongcheng Wang, Comcast

"Building Efficient CNN Models for Mobile and Embedded Applications"
Peter Vajda, Facebook

"Words, Pictures, and Common Sense: Visual Question Answering"
Devi Parikh, Facebook and Georgia Tech

"Improving and Implementing Traditional Computer Vision Algorithms Using DNN Techniques"
Paul Brasnett, Imagination Technologies

"Developing Computer Vision Algorithms for Networked Cameras"
Dukhwan Kim, Intel

"The Roomba 980: Computer Vision Meets Consumer Robotics"
Mario Munich, iRobot

"How to Get the Labeled Data for Free"
Matt King, IUNU

"APIs for Accelerating Vision and Inferencing: Options and Trade-offs"
Neil Trevett, Khronos Group and NVIDIA

"Deep Quantization for Energy Efficient Inference at the Edge"
Hoon Choi, Lattice Semiconductor

"Real-time Calibration for Stereo Cameras Using Machine Learning"
Sheldon Fernandes, Lucid VR

"The Role of the Cloud in Autonomous Vehicle Vision Processing: A View from the Edge"
Ali Osman Ors, NXP Semiconductors

"Creating a Computationally Efficient Embedded CNN Face Recognizer"
Praveen G.B., PathPartner Technology

"Implementing Image Pyramids Efficiently in Software"
Michael Stewart, Polymorphic Technologies

"New Deep Learning Techniques for Embedded Systems"
Tom Michiels, Synopsys

"Deep Understanding of Shopper Behaviors and Interactions Using Computer Vision"
Emanuele Frontoni and Rocco Pietrini, Università Politecnica delle Marche

"Recognizing Novel Objects in Novel Surroundings with Single-shot Detectors"
Alexander Berg, University of North Carolina at Chapel Hill and Shopagon

"What is Neuromorphic Event-based Computer Vision? Sensors, Theory and Applications"
Ryad B. Benosman, University of Pittsburgh Medical Center, Carnegie Mellon University and Sorbonne Universitas

"Utilizing Neural Networks to Validate Display Content in Mission Critical Systems"
Shang-Hung Lin, VeriSilicon

"Building a Typical Visual SLAM Pipeline"
YoungWoo Seo, Virgin Hyperloop One

"Getting More from Your Datasets: Data Augmentation, Annotation and Generative Techniques"
Peter Corcoran, Xperi and C3Imaging

"Hybrid Semi-Parallel Deep Neural Networks (SPDNN) – Example Methodologies & Use Cases"
Peter Corcoran, Xperi and C3Imaging

Technology Showcase Demonstrations

Aquifi

Aquifi

BDTI

BDTI

BDTI

BDTI

BDTI

BDTI

FIRST Robotics

FIRST Robotics

Intel

Intel

NALBI

NALBI

NovuMind

NovuMind

NovuMind

NovuMind

Save the Date: May 20-23, 2019 in Santa Clara, California