An analysis of court cases has revealed that the mistaken identification of the wrong person by victims and witnesses of a crime is the single most common error leading to the arrest and conviction of innocent people [Wells et al. 2006]. Recognizing the role of mistaken identification in erroneous conviction, a growing number of states and police departments have reformed their eyewitness identification procedures. In this paper, we investigate a new procedural reform: the use of a virtual officer who does not know the identity of the suspect in the lineup and therefore cannot bias the witness toward false identification.
|
Officer Garcia is "the man"
Researcher: Brent DaughertyAdvisor: Larry Hodges |
To investigate the effects of using immersive virtual humans to teach users
social conversational verbal and non-verbal protocols in south Indian culture. The results of our study
suggest that participants who trained with the virtual humans performed
significantly better than the participants who studied from literature.
| |
Through an interdisciplinary collaboration, a team of researchers from CS and Biology in UNC-Charlotte and Carolina Medical Center have analyzed the behavior of cells (red, white and natural killer T) in liver with respect to the pathological conditions of trauma and cancer in in vivo images through development of automated cell motion analysis algorithsm.
|
Biomedical Image Analysis
Researchers: Stephen Schmuggge, Jerrod Kraftchick, Nhat Rich NguyenAdvisor: Min ShinCollaborators: Mark Clemens, Toan Huynh, Steve Keller |
We report on a study that compares three different methods of travel in a complex, multi-level virtual environment using a between-subjects design. A real walking travel technique was compared to two common virtual travel techniques. Participants explored a two-story 3D maze at their own pace and completed four post-tests requiring them to remember different aspects of the environment.
| |
The purpose of this project is to investigate the ease of use and efficiency of 3D User Interaction Techniques using a two-handed input device with that of a visualization. In particular we are building a test-bed application for visualizing weather data in western North Carolina. Weather in the mountains of western North Carolina is extremely volatile, therefore many interesting properties can be examined using 3D visualization rather than 2D visualization.
| |
Intravital microscopy has been used to visualize the microcirculation by imaging fluorescent labeled red blood cells (RBCs). Traditionally, microcirculation has been modeled by computing the mean velocity of a few, randomly selected, manually tracked red blood cells. However, this protocol is tedious, time-consuming, and subjective with technician related bias. We present a new method for analyzing the microcirculation by modeling the red blood cell motion through automatic tracking. The tracking of red blood cells is challenging as in each image, as many as 200 cells move through a complex network of vessels at a wide range of speeds while deforming in shape.
|
AutomaticTracking of Red Blood Cells in Intravital Microscopy Images
Researchers: Stephen Schmugge, Walid Kamoun, Jerrod KraftchickAdvisor: Min ShinCollaborators: Mark Clemens |
The purpose of this project is to offer more
realistic training for nurses working in the triage
unit. The nurse can better acquire and practice
interview and assessment skills essential for
working in triage. The nurse verbally conducts
interview with patient, observes, examines, and
diagnoses. The Digital Patient uses speech
recognition interface with natural language
processing to create more natural conversation
between the Digital Patient and the student nurse.
|
Digital Patient for Triage Nurse Training
Researcher: Amy UlinskiAdvisor: Larry Hodges |
We have developed a gesture recognition algorithm using a real-time range scanner (Digiclops), examined the effectiveness of colorspace transform and distribution modeling approaches for skin detection which was used for hand detection, and applied it for tracking hand in virtual human tasks.
|
Biomedical Image Analysis
Researchers: Stephen SchmuggeAdvisor: Min ShinCollaborators: Leonid Tsap |
Answers First is a new methodology for conversational question answering that eliminates this additional cognitive processing step and facilitates a more natural interaction between the user and application/medium. A1 allows the user to speak their question as it is naturally formed in their minds. It matches the question to the question repository, identifies the question with the highest match of terms, retrieves the indexed answer and presents that answer to the user. A1 was first tested via iTech: an interactive technical assistant.
| |
Our research interests include all aspects of digital humans, including interaction, rendering, psychology, and perception. Can digital humans make you cry, laugh, depressed, or elated? How can an object, so obviously not real, elicit such emotions? The fundamental question that this leads to is: Do virtual characters produce the same responses as real characters?
|
Digital Human Project
Researcher: Sab Babu, Amy Ulinski, Cathy Zanbaka, Steve Schmuggge, Evan SumaAdvisor: Larry Hodges |
We compared four different methods of travel in an immersive virtual environment and their effect on cognition using a between-subjects experimental design. The task was to answer a set of questions based on Crook’s condensation of Bloom’s taxonomy to assess the participants’ cognition of a virtual room with respect to knowledge, understanding and application, and higher mental processes. Participants were also asked to draw a sketch map of the testing virtual environment and the objects within it. Users’ sense of presence was measured using the Steed-Usoh-Slater Presence Questionnaire.
|
Effects of Travel Technique on Cognition in Virtual Environments
Researcher: Sab Babu, Amy Ulinski, Cathy Zanbaka, Dan Xiao, Benjamin LokAdvisor: Larry Hodges |
kin detection is an important indicator of human presence and actions in many domains, including interaction, interfaces and security. It is commonly performed in three steps: transforming the pixel color to a non-RGB colorspace, dropping the illuminance component of skin color, and classifying by modeling the skin color distribution. In this paper, we evaluate the effect of these three steps on the skin detection performance.
| |
Skin detection is frequently used as the first step for the tasks of face and gesture recognition in perceptual interfaces for human-computer interaction and communication. Thus, it is important for the researchers using skin detection to choose the optimal method for their specific task. In this paper, we propose a novel method of measuring the performance of skin detection for a task
| |
Since 1993 Dr. Hodges and his students in the Virtual Environments Group have been developing and testing virtual environments that can be used by clinicians in the treatment of different anxeity disorders. Many of these environments are now available commercially through Virtually Better.
| |
