| smartphone.com |
More than 1 billion camera phones will be be put in people’s hands in 2008. That’s a big number. Citizen journalism, instant visual communications... All here, Now! |
Fullpower introduces the The next paradigm shift for mobile is "sensing". The Nintendo Wii as well as screen rotation on the iPhone are examples of simple implementations of motion sensing in mass market devices. To build more advanced sensing solutions, the challenge is similar to that of speech recognition: It takes a lot of technology to get it right. Over the past five years Fullpower has developed the MotionX Recognition Engine, designed to accurately solve the challenges of gesture recognition, pedestrian navigation, and image stabilization among others. In a nutshell, the MotionX Recognition Engine is to motion what a great speech recognition engine is to speech. At the D7 conference Fullpower is presenting two real-world implementations of the MotionX Recognition Engine: Presentation 1, The MotionX-Headset: Complete motion user experience and gesture recognition as well as pedestrian navigation. TapTap™ commands, ShakeShake® commands, power management and accurate measurement of distance and speed traveled using pure accelerometrics. Presentation 2, MotionX-Imaging: Full image stabilization using pure smartphone accelerometrics (something that is reputed impossible to do without expensive specialized sensors and electronics). This solution scales infinitely to very high resolution imaging sensors. Based in Silicon Valley, Fullpower is the world leader for mobile sensing solutions and develops technology and IP with an embedded licensing business model.
|
Accelerometrics: The art of motion sensing. We look around, everything is in motion. When motion slows, life pauses. Motion shapes our lives and gravity defines motion. We want to use gestures to control mobile devices: ShakeShake to roll virtual dice in the iPhone, TapTap to adjust the volume on the headset, Tilt 'n Roll to navigate Google maps. We use motion to control our favorite devices and interpret motion to improve our sports performance and our health. Gravity, Galileo, Newton and Us Gravity keeps us grounded. It's our blessing and our curse. Gravity is the key force that shaped evolution. Accelerometers sense gravity, giving us the signals to understand motion. The ancient Greeks with all their brilliance didn't understand motion, gravity or time very well. More than fifteen hundred years later, Galileo became the father of modern science. Before Galileo, with the prevalence of "Greek Cosmology," heavier things fell faster and the earth was at the center of the universe. Galileo changed everything. He was skeptical of all the grand Greek schemes. He simply used his pulse to measure time and rolled balls of different weights on the same inclines. He carefully marked where each ball came to rest with every heartbeat (about one per second). Careful observation showed that no matter what the weight was, the balls all moved following the same patterns: one unit in one heartbeat, four in two, nine in three and sixteen in four. Galileo created a repeatable and reliable experiment. Later he used water-clocks and pendulums to measure time more accurately. The Greeks were toast and the modern scientific method was invented: observe, reason and experiment. It was the dawn of the 17th century, some three hundred years ago. Newton then took all the pieces, trusted in Galileo's principle of inertia and postulated that there had to be a force that attracted the Earth to the Sun and the Sun to the Earth and everything to everything else in the universe. We still don't understand the nature of that force. But we know that gravity is everywhere, keeping the universe in balance. Walking: Defying Gravity Walking is so natural to humans that we forget the millions of years of evolution that allowed us to defy gravity by standing up and running on our hind legs consistently. Something that most children learn to do before they are two years old essentially defines us as a species. Our head, brain, intellect above all. Standing tall, making weapons, hunting in groups, using tools, and inventing technology has given us humans complete control of the planet. For the better and the worse. Consider this factoid: for every wild 'protected endangered gorgeous wild wolf,' there are more than 1000 pet dogs. The domesticated Canis Lupis seems to have prospered much better than the wolf in the wild. Smart move. We now get to use technology to try to better understand motion. After defying gravity, we get to measure gravity. And for this we use motion sensors. With smaller, more accurate and more power efficient sensors we can embed motion sensing in almost every mobile device. Now we are measuring and interpreting gravity and taking action. Measuring Gravity with Sensors and Calibrating Human Motion Thanks to Newton and Galileo, we know that we can understand motion by measuring acceleration. Cinematics, the science that studies motion, uses high-school calculus to relate acceleration, speed and position. In a mobile device, when we do this in real time we don't really integrate acceleration to get speed and speed to get position. We interpret the signals of the sensors and recognize motion patterns. Just like a good speech recognition engine recognizes words captured by a microphone. We use innovative technology to interpret signals captured by nano-technology based sensors so that our mobiles tell us how fast we are running or walking for example. The science of accelerometers is profound and essential. Satellite based navigation systems are of little use when signals vanish in an urban canyon or a wooded area or when changes in position and motion are unrelated as on a treadmill. Accelerometrics is a cool new discipline. Newton and Galileo would love it. Putting Life and Motion in Control The Wii changed gaming consoles by moving them from the hardcore gamer community to the mainstream. My 11 year old daughter and I love to play Mario Kart with the rest of the family. Great stuff on a big screen. On mobiles, in the palm of our hands, it's a different experience. TapTap, ShakeShake, Tilt 'n Roll are naturals. Motion now controls a whole virtual mobile world. The motion-aware mobile platform is the new media. It is going to be by far the most popular platform in the world as it is just a matter of time before everyone of our billions of motion-enabled co-humans wants one. Because life is motion.
|
Will my favorite Android soon dream of sheep? People use AI as a buzz-word to promote the Roomba vacuum cleaner: That's a great sign! To be fair, it does fit into a definition of AI of a system that perceives the environment and can make intelligent decisions. The kind of decisions that a reasonable human would make. Now imagine if every camera-phone had the ability to "sense the environment" and make "intelligent decisions" that can anticipate and act meaningfully. Then AI comes as a way to help and enhance the lives of real intelligent beings: All of us! AI is present in a system that perceives its environment and takes actions which maximize its chances of success. For example the next generation of sensor-enhanced mobile devices may use enough smarts to qualify as AI-based systems. At least that is what we are working very hard on doing at Fullpower. AI is not just about systems that can learn. I think that for AI, what is more important is understanding the environment and making inferences that maximize chances of success. Learning can be part of the process. It is not necessary or sufficient. By the same token, natural language processing is not automatically AI. It can be. We can use AI techniques as part of a system that does natural language processing. But language is not automatically intelligence. It is communications. For years, the Turing Test was seen as the criterium and the end of it all: If a human communicating using text messages with a machine wasn't able to recognize that he/she was dialoguing with a machine, then that machine had to be "artificially intelligent". The Turing test in my opinion is simply about building a machine good enough to be able to fool a human into believing that it is human through any text message interaction. It's of course always an interesting exercise, but at the end of the day it does not attempt to truly emulate the advanced problem solving abilities of human intelligence. Let alone any form of "social-intelligence" or understanding of the environment via sensors for example. And conversely we can think of many humans who could fail the test themselves yet have "natural intelligence". So the Turning test may just be an interesting exercise, but not a way to characterize machine or human intelligence. As it is many times the case, I think that academia may have gotten a bit stuck with the LISP machines industry and with robots. The thought was to replace human intelligence and/or labor. However things are changing quickly and technology is moving by leaps and bounds. For example, when we all thought that robotics would allow American and European manufacturing to be more competitive, China has become the "factory of the world" without technology by leveraging an endless low-wage hard-working low-skilled workforce. Present day industrial robots are made of just a little bit of AI and a lot of electronics and mechanics. I'd take R2D2 any day! The world of sensor-enabled and enhanced devices with integrated inference engines has the greatest practical promises for AI's long term success. Next generation robots get better! Yes, I'd predict that most of the successful and useful advances will come from sensor-enabled devices and networks of such sensor enabled devices. Both will be important and make significant advances using sensor-enhanced solutions. Yet, as Shakespeare eloquently says: "We are such stuff as dreams are made on." Our robots and machines don't dream yet. Or as Philip K. Dick's masterpiece: "Do Androids Dream of Electric Sheep?" asks is the true test "emotional intelligence"?
|
CELL PHONE, THE RING HEARD AROUND THE WORLD http://www.cbc.ca/doczone/cellphones/video.html The creation of the camera phone starts at about 21:10 and runs through 27:00. Some highlights: The story of the "Camera Phone Birth" at 21 minutes
|
Copyright 2009 smartphone.com