Embedded Vision Insights: September 23, 2014 Edition

Dear Colleague,

Virtual reality (VR) is a hot technology right now, especially for gaming applications. Current market leader Oculus held a developer conference in Hollywood last weekend and wowed attendees with its latest iteration of the Rift headset design, code-named "Crescent Bay". Samsung and Sony are actively developing their own VR gear, the former in partnership with Oculus. And plenty of other companies, such as Vrvana with its Totem head-mounted display (HMD), are waiting in the wings for the market to embrace VR.

There's only one problem, as panelists at an Oculus developer conference session pointed out: While the VR headset's embedded sensors are able to accurately determine your head's orientation, viewing direction and motion, there's currently no integrated way for it to discern what the rest of your body is doing. Are your feet dancing? Are your arms waving? What are your hands, and the fingers attached to them, doing? The Oculus Rift by itself doesn't have a clue, and wrist- and ankle-mounted motion sensor accessories are cumbersome and provide only rudimentary additional data. This means that your own body cannot appear in the virtual world in a realistic way.

Enter embedded vision with the solution. As demonstrated by SoftKinetic's Tim Droz at a recent Alliance Member Meeting, a depth camera mounted to the VR headset is able to see and insert the actions of your hands into the virtual world you're interacting with (complete with accurate gesture recognition). Place a camera elsewhere in your VR "game room", and it's able to view not only the movements of your hands but of your full body. And, as Microsoft's Kinect and Sony's PlayStation 4 Camera reveal, this technology can be sold quite inexpensively, especially when the hardware price is subsidized by content sales.

Another hot technology is augmented reality (AR), which as its name suggests, aspires to information-enhance the real world instead of replacing it. As with VR, it's a compelling opportunity for various embedded vision solutions; see, for example, Qualcomm's recent Vuforia development tools press release from the company's developer conference last week, as well as Ori Inbar's (AugmentedReality.org) presentation at May's Embedded Vision Summit, and a technical article co-authored by several Alliance member companies. And while you're on the Alliance website, make sure you check out all the other great new content published there in recent weeks.

Thanks as always for your support of the Embedded Vision Alliance, and for your interest in and contributions to embedded vision technologies, products and applications. Whenever you come up with an idea as to how the Alliance can better service your needs, you know where to find me.

Brian Dipert
Editor-In-Chief, Embedded Vision Alliance

Google Project Tango: Integrating 3D Vision Into Smartphones
Johnny Lee, Technical Program Lead at Google, delivers a presentation at the May 2014 Embedded Vision Alliance Member Meeting. Project Tango is an effort to harvest research in computer vision and robotics and concentrate that technology into a mobile platform. It uses vision and sensor fusion to estimate position and orientation of the device in real-time, while generating a 3D map of the environment.

A Conversation With Scott Krig, Author of "Computer Vision Metrics: Survey, Taxonomy, and Analysis"
Jeff Bier, founder of the Embedded Vision Alliance, interviews author Scott Krig, who discusses his background in computer vision, his motivations for writing "Computer Vision Metrics," and the breadth and depth of topics it covers. The book is freely available for download from the Alliance website, and a limited number of complimentary print copies are also also available to US-based readers willing to post a review of the book to the discussion forum area of the website.

More Videos

High-Performance Machine Vision Systems Using Xilinx 7 Series Technology
The machine vision market is experiencing unparalleled growth of pixel rates in high-end vision systems. This accelerated growth, already exceeding the Moore's Law trend to which semiconductor manufacturers and markets have become accustomed over the years, presents an immediate and increasing demand for high-performance connectivity that provides, with a minimal number of cables, seamless support for 10G+ link speeds over distances in the range of 100m. This white paper examines the system requirements of such high-performance, leading-edge technology, and highlights the universe of available standards-compliant turnkey machine vision systems designed around the Xilinx® 7 series FPGAs. More

Embedded Vision Enters the Robotic Vacuum Cleaner Market
Dyson recently announced its first robotic vacuum cleaner, the Dyson 360 Eye, which uses a 360 degree camera and embedded vision software to help the product navigate around the home. The Dyson 360 Eye represents a new opportunity for embedded vision in the consumer electronics market. Embedded vision technology enables devices to understand the world around them by analysing video images. The Dyson 360 Eye uses a simultaneous localization and mapping (SLAM) technology to understand its position within a room to more efficiently cover the space. More

More Articles

Free Book Opportunity: "Computer Vision Metrics: Survey, Taxonomy, and Analysis"

I'm Looking for a Computer Vision Expert!

More Community Discussions

Qualcomm Announces Vuforia for Digital Eyewear, Powering the Next Generation of Augmented Reality Experiences

Xilinx, Northwest Logic and Xylon Provide Low Cost FPGA-based MIPI Interfaces for Video Displays and Cameras

Altera and Baidu Collaborate on FPGA-based Acceleration for Cloud Data Centers

More News