intellabs
Latest
Intel Labs measures cognitive workload of distracted drivers, we go eyes-on with the demo (video)
Many studies have shown that any kind of distracted driving is a bad thing, but Intel wanted to take a closer look at our driving behavior to determine if we could avoid it in the first place. Paul Crawford, a senior research scientist in Intel's Interaction and Experience Research Lab, sought to do just that in a comprehensive investigation that seeks to understand not just where drivers are looking, but how they're thinking. By doing this, Intel hopes to alert the driver of any mental warning signs before he or she even gets behind the wheel. At a recent Research @ Intel event in San Francisco, Crawford used a racing car gaming set-up to demonstrate both visual and mental diversions with eye-tracking software and a functional near-infrared spectrometer headband. The latter is used to gauge the metabolic activity and cognitive workload of the brain under different driving conditions, which in this case fluctuated between a peaceful drive and a high-speed chase. Crawford also threw in a few questions and mathematical problems at the test subject to complicate matters. As you might expect, the brain was highly active during the more challenging scenarios and less so in the other. Crawford told us he hopes that the findings will point to ways we can optimize our environmental conditions and taskloads so that we can perform better, not just when driving but in everyday tasks as well. To see the demo in action and hear Crawford's words for yourself, check out the video after the break. Michael Gorman contributed to this report.
Intel Labs developing 'talking' tail lights for safer roads, we go eyes-on (video)
Smarter headlights could guide you out of a rainstorm, but intelligent tail lights could enable communication between vehicles. At least, that's the idea behind a collaborative Connected Vehicle Safety project between Intel and National Taiwan University. Its purpose is so that you'll be able to know just what the vehicles around you are up to -- whether they're speeding or braking or making a left -- by receiving data from their tail lights. Your vehicle could then stop or accelerate automatically without you needing to intervene, or you could choose to react manually if desired. We saw a demonstration of the concept at a Research @ Intel event in San Francisco with a couple of scooters, so head on past the break to learn how it all works, with video to boot.
Intel research projects bring Legos to life, make groceries interactive
Kinect hacks aren't the only projects using depth cameras these days, Intel's Seattle research lab has also been working on a whole range of projects using what it describes "Kinect style" cameras, and it's now showing off some of the results. Among the most interesting are a pair of projects that combine a depth camera with a projector for some rather inventive augmented reality applications. One of those examples can effectively bring Legos to life (as pictured above), while the other adds a whole new degree of interactivity to everyday objects, namely groceries -- which could let you manage a grocery list using actual fruits and vegetables, for instance, or even warn when you've left a tub of ice cream sitting on the counter too long. That's just scratching the surface, though -- the group has also devised a system that can map a room just by walking around with a depth camera, which can then of course be navigated using the very same depth camera and a pair of 3D goggles. Head on past the break for a couple of videos, and hit up the source link below for the rest.
Intel's smart TV remote will recognize you, tailor content to your wishes
It's all about how you hold it, apparently. Intel's Labs have churned out a proposal for a new user-identifying system to be embedded into remote controls. Given a bit of time to familiarize itself with particular users, this new motion sensor-equipped channel switcher is capable of correctly recognizing its holder just by the way he operates it. Taking accelerometer readings every 100 nanoseconds, the researchers were able to build a data set of idiosyncrasies about each person, which would then be applied the next time he picked up the remote. Alas, accuracy rates are still well short of 100 percent, but there's always hope for improving things and for now it's being suggested that the system could be employed to help with targeted advertising -- which is annoying anyway, whoever it may think you are.
