Just a few years ago, it was inconceivable that everyday devices would incorporate visual intelligence. Now it’s clear that visual intelligence will be ubiquitous soon. We invite you to join us in Santa Clara on May 1-3 to discover the latest market and technology trends and hear how industry leaders are bringing value to a wide range of industries using computer vision.
Editor-In-Chief, Embedded Vision Alliance
3D VISION OPPORTUNITIES
High-resolution 3D Reconstruction On a Mobile Processor
Computer vision has come a long way. Use cases that were previously not possible in mass-market devices are now more accessible thanks to advances in depth sensors and mobile processors. In this presentation, Michael Mangan, Product Manager for Camera and Computer Vision at Qualcomm, provides an overview of how we are able to implement high-resolution 3D reconstruction – a capability typically requiring cloud/server processing – on a mobile processor. This is an exciting example of how new sensor technology and advanced mobile processors are bringing computer vision capabilities to broader markets.
Getting from Idea to Product with 3D Vision
To safely navigate autonomously, cars, drones and robots need to understand their surroundings in three dimensions. While 3D vision has been studied in academia for decades, it has only recently begun to be incorporated into commercial systems. For system developers, 3D vision brings a slew of new concepts, terminology, and algorithms – such as SLAM, SFM and visual odometry. This talk from Anavai Ramesh, Senior Software Engineer at Intel, and Avinash Nehemiah, Product Marketing Manager for Computer Vision at MathWorks, focuses on challenges engineers are likely to face while incorporating 3D vision algorithms into their products and discusses practical approaches to solving these problems in real-world autonomous systems.
APPLICATION DEVELOPMENT AND COMMERCIALIZATION
Democratizing Computer Vision Development: Lessons from the Video Game Industry
Computer vision offers great promise: algorithms are maturing rapidly and processing power continues to grow by leaps and bounds. But today’s approach to computer vision software development – hiring a team of computer vision PhDs to hack OpenCV – is not scalable and represents a major bottleneck to mass deployment of vision-enabled products. The video game industry faced similar challenges in the early 2000s, when it became impractical for game developers to write an entire game engine from scratch. Today, small teams of independent game developers leverage commercial game engines like Unity to build complex video games that only five years ago would have required a 100+ person team. In this talk, based on experience in the game industry, Paul Kruszewski, President of WRNCH, predicts how computer vision software development will evolve to enable creation of thousands of new vision-enabled products. He also shares ways that managers and entrepreneurs can avoid the most serious pitfalls of vision software development today.
A Practitioner’s Guide to Commercializing Applications of Computer Vision
Computer vision technology is advancing at an exciting pace, but still has a long way to go toward maturity and realizing its full potential. The technology itself presents attractive opportunities, but the opportunity presented by the applications it will enable dwarfs this. The ultimate possibilities are limited only by the imagination and insights of professionals across industries, but how do we assess what applications are feasible today? What attributes do today’s applications have in common, and how do we go about realizing them? This presentation from Peter Shannon, Managing Director at Firelake Capital Management, explores the practical implications of commercializing a vision-enabled product, from product requirements to development expectations through to validation and ensuring a good customer experience, highlighting the points of contrast with the commercialization of more traditional software-based products.