Herman Yau, Co-Founder and CEO of Tend, presents the "Vision-as-a-Service: Democratization of Vision for Consumers and Businesses" tutorial at the May 2015 Embedded Vision Summit.
Hundreds of millions of video cameras are installed around the world—in businesses, homes, and public spaces—but most of them provide limited insights. Installing new, more intelligent cameras requires massive deployments with long time-to-market cycles. Computer vision enables us to extract meaning from video streams generated by existing cameras, creating value for consumers, businesses, and communities in the form of improved safety, quality, security, and health.
But how can we bring computer vision to millions of deployed cameras? The answer is through "Vision-as-a-Service" (VaaS), a new business model that leverages the cloud to apply state-of-the-art computer vision techniques to video streams captured by inexpensive cameras. Centralizing vision processing in the cloud offers some compelling advantages, such as the ability to quickly deploy sophisticated new features without requiring upgrades of installed camera hardware. It also brings some tough challenges, such as scaling to bring intelligence to millions of cameras.
In this talk, Herman explains the architecture and business model behind VaaS, shows how it is being deployed in a wide range of real-world use cases, and highlights some of the key challenges and how they can be overcome.