Research Terms
Computer Simulation and Modeling Computer Graphics Computational Complexity
Industries
Digital Media Modeling, Simulation, & Training (MST)
Journal
1. P. Varcholik, J. J. LaViola and C. E. Hughes, “An Exploration of Multi-Touch Input for Text Entry,” International Journal of Human-Computer Studies, in press.
Researchers at the University of Central Florida have invented computer simulation technologies to help people with environmental anxiety disorders improve their executive functioning (EF) skills. The technologies may help people with conditions such as autism spectrum disorder (ASD), post-traumatic stress disorder (PTSD), and attention deficit disorder (ADD). EF includes cognitive brain processes, such as inhibition, memory, attention, emotional regulation, planning and problem-solving.
The new technologies provide dynamic virtual environments for learning, practicing and improving EF skills—capabilities unavailable in existing technologies. The inventions offer those with sensory overload, such as people with ASD, ways to experience real-world situations safely. For example, a student who may be anxious about a doctor's visit, asking out a peer on a date, or asking for help in a situation can use the technologies to practice and master such skills.
Technical Details
The UCF inventions replicate interactions found to transfer EF skills back into the home, school, and community life of individuals and enable repeated practice. Specific objectives for EF skills are set in the environment with computer-automated avatars interacting in a controlled setting. The apparatus generally consists of sensors, video displays, computer processors, and memory storage devices.
Once tasked with an EF skill, an individual is fully or partially immersed in a computer-simulated environment for a time-limited session. The system monitors the individual in real-time, using sensors to detect quantifiable changes in anxiety level.
A common characteristic of the EF skill assigned is that a sufficient increase in anxiety state by the individual hinders successful completion of the skill. In response to an individual’s increased anxiety level, the computer-simulated environment modulates the sensory complexity of one or more simulation features to enable the individual to develop proficiency in EF skills in increasingly complex environments therapeutically. The intensity of a scenario can be escalated or de-escalated depending on the objective, tolerance, and the desired outcome specified by the intervention team aligned with learning versus mastering an EF skill.
In one application, an individual suffering from flight anxiety may be immersed in a virtual, augmented, or mixed reality environment simulating the cabin of a commercial aircraft. The computer simulation may include vibrations and tilting of the subject's chair to simulate takeoffs, landings, and turbulence. The person running the simulation can modify the intensity by controlling the number of passengers (typically automated avatars), the behaviors of the passengers (such as belligerent passengers, crying children, sleeping passengers), ambient noise levels, and dialog loops of the automated avatars.
Partnering Opportunity
The research team is seeking partners for licensing and/or research collaboration.
Stage of Development
Prototype available.
Researchers at the University of Central Florida have devised an improved system, method, and computer readable media for real-time chroma key matting by using image statistics. Chroma keying is a special effects or post-production technique for layering two images or video streams together based on color hues. This new technology operates in real-time, functions in visually noisy environments, and simplifies calibration. Prior techniques have required low signal noise, significant calibration, and do not operate in real-time. The UCF invention meets the need for an affordable, robust, and fast matting process that works with low-quality video signals, less than perfect lighting environments, and non-uniform matting material.
Technical Details
The UCF approach is different from other technologies in that it incorporates the use of a processor and preferably uses the Graphic Processing Unit (GPU) of the computer, thus freeing up CPU cycles for other real-time operations. An alpha matte is generated from a video signal based on the chroma key information in real-time via pixel shaders. To accomplish this, princial components analysis (PCA) generates a linear transformation matrix where the resulting color triplet's Euclidean distance is directly related to the probability that the color exists in the chroma key spectrum. The result of this process is a trimap of the video signal's opacity. To solve the alpha matte from the trimap, an energy function constrained by the trimap is minimized with gradient descent. This energy function is based on the least-squared error of overlapping neighborhoods around each pixel and is not dependent on the background or foreground color. The resulting alpha matte is processed within the GPU, is easy to calibrate, robust to noise and operates at exceptionally high frame rates. An optional error minimization stage improves the estimated matte, accounting for misclassifications and signal noise. Given the resulting matte, standard alpha blending composites the virtual scene with the video feed to create the illusion that both worlds coexist.
