Tim Hartley, Product Manager in the Personal Mobile Compute Business Line at ARM, presents the "Lessons Learned from Bringing Mobile and Embedded Vision Products to Market" tutorial at the May 2016 Embedded Vision Summit.
Great news: technology is finally at a point where we can build sophisticated computer vision applications that run on mass market devices, like mobile phones and cars and vacuum cleaners. Not-so-great news: developing vision applications is hard — maybe uniquely so. Technical and business challenges abound. Developers can quickly come up against thermal and power limitations. Software may perform well on one platform, but poorly on another, similar platform. These are some of the problems that can sink your product.
In this talk, Hartley presents case studies in which various computer vision challenges put product development at risk, and explores how they are being addressed by leading product developers. What lessons are there for businesses working in this area? What key challenges remain to be overcome to enable ubiquitous visual intelligence?