Software developed by the University of Bristol is putting expressions on the face of Jules

Software developed by robotics engineers from the University of Bristol is putting a smile, frown, and many other expressions on the face of Jules, an animatronic head.

Human face movements are picked up by a video camera and mapped onto the 34 tiny electronic servo motors in Jules’ flexible rubber skin. The Bristol team developed its own software to transfer expressions recorded by the video camera into commands to make those servos produce similarly realistic facial movements.

However, because the robot’s motors are not identical to human facial muscles, some artistic licence was required. After filming an actor making a variety of expressions indicating, for instance, ‘happiness’, an expert animator selected 10 frames showing different variations of the expression and manually set the servos in Jules’s face to match.

In addition to performing tasks such as security control and surveillance monitoring, age-estimation software also could be used for electronic customer relationship management or to target specific audiences with advertising, said Thomas S. Huang, the William L. Everitt Distinguished Professor of Electrical and Computer Engineering at the U. of I.

People who hope to keep their age a secret won’t want to go near a computer running this software.

Like an age-guesser at a carnival, computer software being developed at the University of Illinois can fairly accurately estimate a person’s age. But, unlike age-guessers, who can view a person’s body, the software works by examining only the person’s face.

“Age-estimation software is useful in applications where you don’t need to specifically identify someone, such as a government employee, but would like to know their age,” said Thomas S. Huang, the William L. Everitt Distinguished Professor of Electrical and Computer Engineering at the U. of I.

For example, age-recognition algorithms could stop underage drinkers from entering bars, prevent minors from purchasing tobacco products from vending machines, and deny children access to adult Web sites, said Huang, who leads the Image Formation and Processing group at the university’s Beckman Institute.
Continue reading…

A high-tech virtual training package is being used by the British military to help train military personnel being deployed to Afghanistan and Iraq.

The Joint Combat Operation Virtual Environment (JCOVE) contains entire virtual towns modelled in detail on their real-life counterparts in Iraq, as well as insurgents with AK47s, roadside bombs, suicide bombers and civilians. The software also incorporates much of the latest British military hardware including Challenger and Warrior Armoured vehicles, WMIK Land Rovers, Logistic Trucks and Mastiffs. Weapon systems include the SA80 rifle, Minimi machine guns and grenades; and air assets including Apaches, Chinbooks and Predator Unmanned Aerial vehicles.

The package can be used for teaching procedures and tactics for numerous combat scenarios, but at present it is primarily being used to teach soldiers in the Royal Logistic Corps (RLC) the procedures for driving in convoys.

Continue reading…

Researchers at the University of Aberdeen have designed an interactive program that can help sufferers of partial vision loss (hemianopia), which is caused by damage to the visual pathways in the brain after a stroke.

The Neuro-Eye Therapy (NeET) uses a medical device called the Vision Rehabilitation Program to repeatedly stimulate blind areas of vision using on-screen patterns.

Dr Arash Sahraie, University of Aberdeen, explained: “The basic principles behind Neuro-Eye Therapy are similar to those of physiotherapy following a stroke. If muscles are affected following a brain injury, patients are asked to repeat a pattern of limb movements in order to improve their mobility.

Continue reading…

A research project designed to help doctors detect subtle changes in the condition of critically ill premature babies has been launched by IBM and the University of Ontario Institute of Technology (UOIT).

A group of researchers will use advanced stream computing software developed by IBM Research to work towards enhancing the decision making capabilities of doctors. The software ingests a constant stream of biological data such as heart rate and respiration, along with environmental data gathered from advanced sensors and more traditional monitoring equipment on or around the babies.

The type of information that will come out of the research project is not available today. Currently physicians monitoring ‘preemies’ rely on a paper-based process that involves manually looking at the readings from various monitors and getting feedback from the nurses providing care.

Continue reading…

Antivirus software on your personal computer could become a thing of the past thanks to a new “cloud computing” approach to malicious software detection developed at the University of Michigan.

Cloud computing refers to applications and services provided seamlessly on the Internet.

Traditional antivirus software is installed on millions of individual computers around the world but according to researchers, antivirus software from popular vendors is increasingly ineffective. The researchers observed malware, malicious software, detection rates as low as 35 percent against the most recent threats and an average window of vulnerability exceeding 48 days. That means new threats went undetected for an average of seven weeks. The computer scientists also found severe vulnerabilities in the antivirus engines themselves.

Continue reading…

Based on the ‘dragonfly’, the DelFly Micro Air Vehicle (MAV) from TU Delft, is an ultra-small remote-controlled, camera equipped aircraft, with the potential for use in observation flights in difficult to reach or dangerous areas.

The MAV barely weighs 3g – 1g of which is the weight of the battery. It can fly for approximately three minutes, and has a maximum speed of 5m/s.

The DelFly has a tiny on-board camera that transmits signals to a ground station. Using software developed by TU Delft, objects can be independently recognised.

In the next step of the project, TU Delft plans to develop the DelFly NaNo, which will measure 5cm and weigh 1g.

Robots that can understand grief or happiness or anger, could soon become a reality with technology currently being developed by Felix Growing.

According to the company, software will allow the robot to learn when a person is feeling a certain way. Using cameras and sensors, the robots will be able to detect several variables from the human including their facial expression, voice, and tone. It will then combine the factors to determine what mood the person is in.

Continue reading…

Visualisation specialist See3D, has been commissioned to develop computer-generated models designed to help doctors improve the diagnosis and treatment of prostate cancer.

The development of prostate cancer at an early stage is often difficult to diagnose, depending on where the cancer is located. See3D’s visualisation project, commissioned by Oncomorph Analysis, will over the next two years, identify smaller cancerous regions of the prostate that are currently undetectable to doctors, by the rapid processing of numerical data. Doctors can then use this information to aid diagnosis and subsequently treatment.

Continue reading…