Marathon Robotics and the Australian Defense Force teamed up to bring realism and a little fun to snipers in training. They outfitted Segways with foam bodies in hoodies for live-fire sniper training. With the Rover system, there is no joystick -- the Segways are pre-programmed to follow a planned scenario. When a target is shot, it provides instant visual feedback by stopping and dropping its mannequin, and sends a message to other Segways to scatter.
Now, if only someone could program them to dance to "Thriller"!
The Defense Advanced Research Projects Agency's Legged Squad Support System (LS3) program is a joint effort between DARPA’s Tactical Technology Office and the U.S. Marine Corps Warfighting Lab.
The program's goal is to develop a walking quadruped platform to help carry equipment autonomously. These platforms will be capable of managing rugged and complex terrain, where tactical vehicles are not able to go -- lightening the load of Marines and soldiers, and increasing their combat capability.
LS3 will carry 400 pounds or more of payload, and provide 24 hours of self-sustained capability over 20 miles. LS3 will weigh no more than 1,250 pounds (including its base weight, fuel and payload of 400 pounds).
Key LS3 program themes are:
(i) Quadruped platform development: design of a deployable walking platform with sufficient payload capacity, range, endurance, and low noise signature for dismounted squad support, while keeping weight and volume scaled to the squad level.
(ii) Walking control: develop control techniques that allow walking, trotting, and running/ bounding and capabilities to jump obstacles, cross ditches, recover from disturbances, and other discrete mobility features.
(iii) User Interface (to include perception technologies): the ability for the vehicle to perceive and traverse its immediate terrain environment autonomously with simple methods of Marine/Soldier control.
New miniature camera technology -- with the thickness of two stacked credit cards -- that can track the enemy in dark caves and urban alleys, and identify a person from an iris scan, is being field-tested for military and security uses.
Panoptes is an ultra-slim smart camera that combines images from low-resolution imagers to create a high-resolution image. The large number of tiny imagers are directed independently by a MEMS-controlled micro-mirror. Because there is no protruding lens, Pantoptes can be made flat.
A central processor combines the images into a single picture, producing a higher resolution than the individual imagers. The intelligent system can identify areas of interest -- for example, a face -- and concentrates the sub-imagers on only the area of interest -- the iris.
As Marc Christensen, project team leader at Southern Methodist University, explained, “After a first frame or two was collected, the system could identify that certain areas, like the open field, had nothing of interest, whereas other areas, like the license plate of a car parked outside or peering in the windows, had details that were not sufficiently resolved. In the next frame, subimagers that had been interrogating the field would be steered to aid in the imaging of the license plate and windows, thereby extracting the additional information.”
The resulting image is produced without "noise," and frame rates of 30 to 60 per second can be achieved using a normal digital signal processor.
Applications for this technology include military, border patrol and airports.
The new applications may be ready for demonstrations as soon as late 2011, said Christensen.
RoboSwift is a micro airplane that is modeled after a common bird. It carries a mini-camera for discreet surveillance and sends footage wirelessly to a remote monitor. The airplane’s “feathers” fold backwards and its tail planes are transparent, creating a surprisingly lifelike effect.
RoboSwift was designed by a student team from the Netherlands as part of a competition to create innovative unmanned micro-aerial and ground vehicles.
The problem with using voice recognition as a biometric is its slow processing speed.
However, researchers at North Carolina State University are attempting to improve the speed of speech authentication, without sacrificing accuracy.
According to the research paper, “Joint Frame and Gaussian Selection for Text Independent Speaker Verification,” the research is based on Gaussian selection, a technique applied in the GMM-UBM framework to accelerate score calculation. The researchers modified the method known as sorted GMM (SGMM). SGMM uses scalar-indexing of the universal background model mean vectors to achieve fast search of the top-scoring Gaussians. They extended this method by using 2-D indexing, which leads to simultaneous frame and Gaussian selection. The results on the NIST 2002 speaker recognition evaluation corpus indicate that both the 1- and 2-D SGMMs outperform frame decimation and temporal tracking of top-scoring Gaussians by a wide margin.
Voice recognition technology can be used to prevent ID theft and data protection for the government, financial, healthcare and telecommunications sectors.
Simon the Robot, developed by the Georgia Institute of Technology's Socially Intelligent Machines Lab in an effort to study human-robot interactions, showed off his learning abilities at the Computer Human Interaction conference in Atlanta this week.
With his computer vision, ability to respond to questions, identify items and match colors, voice recognition, facial recognition -- thanks to faceAPI from Seeing Machines -- and sound localization, Andrea Thomaz, Simon's creator, hopes Simon will be able to operate successfully in the real world one day.
At the conference, a researcher asked Simon, "Simon, can you hear me?" Simon responded "Yes." The researcher then asked him if he wanted to learn something and Simon reached out his robotic arm, grabbed the object -- a blue book -- and brought it to his face. He was told to put the book in the blue bin, and Simon dropped the book in the bin and said, "There you go."
The researchers' goal is for Simon to learn to do things on his own, without being programmed or prompted every time.
MotionPortrait’s amazing PhotoSpeak 2.0 takes iPhone apps to the next level. The image-processing technology turns photos into “living, breathing” 3-D movies on your iPhone screen.
Interact with your “avatar” by prodding the screen with your finger—you’ll see your image blink and move—or make it speak by recording your own voice. The Visual Voicemail feature lets you send avatar messages to friends. Users can even manipulate celebrity photos and cartoon characters to create parrot-like avatars—because who hasn’t wondered what it would be like to see the Mona Lisa speaking Japanese?
Since Chatroulette's inception, the site's notorious genital-flashers have been driving off advertisers and normal folks more than the founders would like to admit. But now, thanks to a Business Insider contest called “Solve Chatroulette's Penis Problem and Help It Make Billions and Billions,” facial recognition may be coming to the rescue.
The contest winner, John Spyers, a senior project manager from Missouri, explains:
"Not one of the people I've encountered displaying their wares on Chatroulette shows their face. So, utilize a facial recognition scan or brief eye tracking scan before making connections. If there's no facial recognition, then pixilate [the] image and prompt to accept cam feed."
Why not go the other way and do penis recognition? The technology would be too easily fooled by a banana or other phallic object, Spyders said. And apparently a lot of people eat bananas on Chatroulette.
My iPhone has changed the way I navigate through life, but it -- by itself -- can't save my life...yet.
Homeland Security's Science and Technology Directorate's Cell-All is an initiative that aims to equip cell phones with life-saving capabilities; for example, protecting against toxic chemicals.
The design would include a VOC sensor that will intermittenly test air samples to detect and identify toxic chemicals and automatically send an alert to the cell phone user via text, call or chime, as well as to a central station with the time, location and the compound.
Detection, identification and notification all take place in less than 60 seconds. And when a central station is flooded with alerts, false alarms are eliminated, enabling first responders to react faster.
As for privacy issues, Cell-All will operate only on an opt-in basis and will transmit data anonymously. Forty prototypes that can detect carbon monoxide and fires are expected in about a year.
Auto Smiley is computer vision software that detects when you smile into your webcam, and then sends a corresponding smiley face to your computer. The emoticon will pop up in the front-most application, such as a chat window. The app promises to flood your chats with even more unnecessary emoticons; let’s hope LOL and ROFL computer vision isn’t next.
Stephen Russell is an entrepreneur, investor, writer, and all-around-believer in the power of technology to reshape the world. His most recent venture, 3VR Security, is dedicated to building innovative new products, technology, and services for physical security.
