Qualcomm – Spime Wrangler

Announcements featuring Augmented Reality are numerous at CES this year. When one steps back from the noise, it appears, as it has most of 2011, that the buzz is primarily coming from the hardware side of the ecosystem. In the limited time I have to absorb from the deluge of CES news I can't begin to capture everything, but just consider:

Sensics is demonstrating the Natalia line of products based on SmartGoggles technology. This was announced last week, but the models are being tried on by bloggers so we are beginning to get "hands on" reporting.
Vuzix is demonstrating its latest model of SMART see-through eyewear for AR, here's the piece published on CNET about them
Lumus, which has kept quiet the past few years, is showing its latest model of see-through hands-free AR eyewear. Nice photos and comparison on TheVerge blog
Pioneer Electronics automotive division is showing its Heads Up display for AR while driving
Texas Instruments is introducing AR as part of OMAP, as a result of collaborations with Total Immersion and metaio
Qualcomm is showing the results of its collaboration with Sesame Street characters, Bert and Ernie
Freescale Semiconductor is showing gaze tracking and AR for home medical applications
CEVA announces that its latest is CEVA-MM3101 is designed for Camera-Enabled Devices

Where are Intel, ARM, NVIDIA, Imagination Technologies and the other important chip vendors with their eye on mobile?

One can argue if Nokia is a hardware or a software company but it's all three: hardware/devices, software/applications and services/navigation. Nokia's City Lens, being demonstrated at CES, is a great example of urban AR. It's not clear which cities will have it or how many POIs there are. It looks like its only available on the Nokia Lumia 900′s at the moment. Uses onboard sensors to change view modes (held flat, the map shows up on the screen, held upright, list view shows up). OK, so it's rotation-aware. I wonder if this uses any Wikitude technology.

A notable exception to this hardware-centric line-up is Aurasma's announcement about its new 3D engine. Adding 3D puts the platform practically on par with Total Immersion and metaio, at least in terms of feature sets. The technology is featured in a video spot on the LA Times Web site. This and another nice piece in The Guardian is great for raising consumer awareness of AR. The Guardian wrote about the pterodactyl flying around Big Ben. And a video showing a prehistoric monster invading Paris.

There's enough AR-related news and excitement in the first three days of this week to fill a month!

ElipseAR-Cloud Image Recognition

There's long been a debate among computer vision experts between those who envisage feature extraction and matching in the network and those who implement it on the device. There are many factors one must consider and trade offs that must be made but in the end everything boils down to cost: what can you gain by where you put the different tasks if the tasks must be done in real time. For many applications, feature extraction is a bottle neck due to lack of computational power. Qualcomm's AR SDK is an example of device-based recognition.

ElipseAR, a startup based in Madrid, Spain, is heavily on the network side of the debate. They are planning to release a set of tools for markerless (feature-based) Augmented Reality and Computer Vision development that will make image matching and tracking, 3D animation rendering, geolocation using the camera view, face recognition easier to integrate into AR applications. Existing AR apps? Future AR apps?

The company's web site clearly makes a distinction between image recognition, image tracking and matching. What's not clear at the moment, because their position differs depending on which page you are reading, is how much of the ElipseAR processing is to happen within the device and how much will be in the network. They also may be confusing "image" with real time video recognition.

At the moment the company says it will offer its tools for commercial use at no charge. The beta program started in early July and is expected to run until the end of 2011.

Tests must be conducted in real world circumstances to measure the merits of the new algorithm and its architecture. It will be compared against not only other network-based image recognizers such as kooaba, but also other SDKs that have been out for much longer such as Qualcomm AR SDK, Qconcept and others. It's difficult to imagine, for example, ElipseAR getting out ahead of String Labs which released their code June 16, 2011.

Even if the reliability of the ElipseAR algorithms and architecture prove to be up to industry benchmarks, there will continue to be latency out of the control of the developer or user in the cellular networks. There have been rumors that the network "effect" can be overcome, but this will never be a universally reliable solution because coverage of mobile networks is and never will be 100%.