Bookmark and Share

Computer Vision for Augmented Reality in Embedded Designs

Register or sign in to access the Embedded Vision Academy's free technical training content.

The training materials provided by the Embedded Vision Academy are offered free of charge to everyone. All we ask in return is that you register, and tell us a little about yourself so that we can understand a bit about our audience. As detailed in our Privacy Policy, we will not share your registration information, nor contact you, except with your consent.

Registration is free and takes less than one minute. Click here to register, and get full access to the Embedded Vision Academy's unique technical training content.

If you've already registered, click here to sign in.

See a sample of this page's content below:


Augmented reality (AR) and related technologies and products are becoming increasingly popular and prevalent, led by their adoption in smartphones, tablets and other mobile computing and communications devices. While developers of more deeply embedded platforms are also motivated to incorporate AR capabilities in their products, the comparative scarcity of processing, memory, storage, and networking resources is challenging, as are cost, form factor, power consumption and other constraints. Fortunately, however, by making effective use of all available compute capabilities in the design, along with leveraging APIs, middleware and other software toolsets, these challenges are largely and increasingly surmountable.

Augmented reality (AR) and related technologies such as Microsoft's HoloLens and other "mixed reality" platforms are, along with virtual reality (VR), one of the hottest topics in technology today. Applications such as Pokémon Go have generated widespread awareness of AR in the general public, both Apple and Google have recently launched software development kits (ARKit and ARCore, respectively) to further cultivate developer activity in this area, and available middleware toolsets also promise to enable broad multi-platform support while simultaneously maximizing application efficiency on each target platform.

However, many of the existing implementations are based on smartphones and tablet computers, which are the primary topic focus of a previously published article in this series. While these platforms have cost, power consumption, and form factor challenges, they typically also offer an abundance of heterogeneous compute resources (multi-core CPUs, GPUs, DSPs, dedicated-function coprocessors, etc.), memory resources, and robust network connectivity. What about platforms that aren't resource-blessed: head-mounted displays (HMDs), smart glasses, automotive heads-up displays (HUDs), and the like?

This...