Adding Visual AI or Computer Vision to Your Embedded System: Key Things Every Engineering Manager Should Know


Visual AI and computer vision are bringing compelling capabilities to many types of systems -- making them safer, easier to use, more efficient and more capable.  But visual AI and computer vision are quite different from traditional embedded technologies, and for many product development groups, these new technologies bring unfamiliar challenges and unexpected risks.

How can you gain confidence that your requirements can be met with today’s technology?  What metrics should you use to assess accuracy?  Will you need to collect and label your own training data?  Will you need a much more powerful (and expensive and power-hungry) processor?  How will you keep your algorithms up to date as their environment changes? 

Join Jeff Bier and Phil Lapsley from the Edge AI and Vision Alliance, who will take you on a quick course in managing visual AI projects for embedded systems.  We’ll cover how data is now your best friend, and maybe also your worst nightmare (and what you can do to stay on its good side); we’ll look at the iterative nature of AI/CV projects and how that differs from traditional development; we’ll talk about the importance of requirements and real-world versus laboratory conditions; we’ll touch on important issues of bias; we’ll provide an overview of how to think about accuracy; and we’ll give tips on how to talk to your management about a development process that is likely a bit different than what they’re used to.
Jeff Bier Jeff Bier
Founder, Edge AI and Vision Alliance, President, BDTI
Edge AI and Vision Alliance

Jeff Bier is founder of the Edge AI and Vision Alliance, a partnership of 100+ leading technology companies, and is Program Chair of the Embedded Vision Summit, the leading conference for professionals who are incorporating computer vision and edge AI into products. The Edge AI and Vision Alliance works to enable product creators to use practical computer vision and edge AI to solve real-world problems, and to help companies find their best opportunities in this burgeoning space. Jeff is also president of BDTI, an engineering consulting firm. BDTI helps companies incorporate visual AI into systems, and performs in-depth evaluations of processors, development tools, and algorithms. Jeff earned his B.S. and M.S. degrees in electrical engineering from Princeton and U.C. Berkeley. He is a frequent invited speaker at conferences and universities around the world.
Phil Lapsley Phil Lapsley
Vice President of Special Projects, BDTI
Edge AI and Vision Alliance

Phil Lapsley is a co-founder of BDTI, an engineering consulting firm, where he is Vice President of Special Projects. In that role he leads consulting engagements in devising and implementing algorithms for edge AI and computer vision on embedded processors. He is the author of two books and an Internet standard, contributed to Berkeley UNIX, and holds 25 patents. He earned his B.S. and M.S. degrees in electrical engineering and computer sciences from U.C. Berkeley and an MBA from the MIT Sloan School of Management. His technical interests include edge AI/ML, computer vision, deep neural networks, signal processing, and computer/network security.