Sorry, you need to enable JavaScript to visit this website.


Visit the homepage of UK's Center for Visualization and Virtual Environments. Within the area of its research mission, the center contributes to the New Economy of the Commonwealth of Kentucky through education and training programs, partnerships with industry and government agencies and commercialization of intellectual property produced by the research.

Digital Unwrapping of Ancient Scrolls

Researcher: Dr. Brent Seales

From ancient times, words have been recorded that express immortal ideas and thoughts about society, culture and philosophy. Around the world, people have recorded these writings in a variety of ways. However, we are now more aware than ever of the possibility of losing these recordings of human history.

Seales and his team are using 21st century technology to preserve the traces of ancient cultures before the relics disappear forever. The EDUCE project (Enhanced Digital Unwrapping for Conservation and Exploration) is developing a hardware and software system for the virtual unwrapping and visualization of ancient texts. The overall purpose is to capture in digital form fragile 3D texts, such as ancient papyrus and scrolls of other materials using a custom built, portable, multi-power CT scanning device and then to virtually "unroll" the scroll using image algorithms, rendering a digital facsimile that exposes and makes legible inscriptions and other markings on the artifact, all in a non-invasive process.  read more

Computer Vision and Image Processing

Dr. Nathan Jacobs does research to understand long sequences of imagery, particularly imagery from large networks of cameras.  Much of his work has focused on data collected from the glocal network of outdoor webcams.

We consider the special case of tracking objects in highly structured scenes.  In the context of vehicle tracking in urban environments, we offer a fully automatic, end-to-end system that discovers and parametrizes the lanes along which vehicles drive, then uses just these pixels to simultaneously track dozens of objects.  


Researcher: Dr. Ken CalvertDr. James GriffioenDr. Jane HayesDr. Nathan JacobsDr. Victor MarekDr. Brent Seales, Michael Seigler, Suzanne Smith, Dr. Mirek TruszczynskiDr. Ruigang Yang

The over-arching objective of Image-Net is to demonstrate elevated war-fighter preparedness through enhanced battle management imaging technology, real-time mission preparation, and advanced mission training.

The Image-Net program was focused on advancing critical 3D imagery/scene generation producation, display, and dissemination technology to meet USASMDC needs. Taking the most promising imaging technology ideas from the UK Team’s research laboratory and developmental experience, the Image-Net program strove to readily adapt and enhance them to meet the most critical and urgent warfighter needs. The intent is to switch from archived and time-delayed 2D imagery to near real-time 3D enhanced scene generated data streams that will allow warfighters the latest situational awareness in planning and rehearsing their upcoming missions.

The video to the right shows an example of each of the five areas of research and development contained withing the Image-Net project.

Image Geolocalization

Researcher: Dr. Nathan Jacobs

Determining where an image was taken and geolocating depicted structures are important tasks for an image analyst.  For example, the image might show terrorist training facilities or the vicinity of a safe house.  To geolocalize today, the analyst must combine prior knowledge of the area with subtle clues from the image, and then manually search GIS reference data.  This process is extremely challenging, time-consuming, and often yields poor accuracy.  The goal of this project is to develop methods for solving this challenging problem by combining the insight of analysts with the power of automated analysis for Internet scale, geolocation-driven data mining. 

The image to the right shows a collection of pictures from a static camera that highlights several localization cues, the most obvious of which is the sun position. 

ContextualEyes: A Context-Aware Surveillance System

Researcher: Dr. Nathan Jacobs

Today, essentially all images come with GPS data and a time-stamp, but unfortunately most automated image analysis algorithms were not designed with this in mind.  In this project, we are developing algorithms that use the location and time that an image was captured to improve performance.  In addition, we are developing algorithms that extract geospatial information directly from the imagery.  read more

The image to the right shows a collection of scenes used for evaluating ContextualEyes algorithms.

Artificial Intelligence

Consistency Checking of Natural Language Temporal Requirements

Researchers: Wenbin Li, Dr. Jane HayesDr. Miroslaw Truszczynski

We have the problem of identifying inconsistencies in temporal requirements expresses as natural language text.  To this end, we introduce a partially automated approach to minimize analysts workload.  We create a language with a formal syntax and formal semantics, to provide a means to represent natural language requirements precisely and unambiguously.  We call this language Temporal Action Language (TAL).  TAL allows actions of different durations and provides a means for formally stating temporal constraints.

Computational Morphology

Researchers: Dr. Raphael Finkel, Dr, Gregory Stump (English)

We investigate the morphology of natural languages by using both generative and analytical tools.  Generative tools include KATR, an extension of DATR for implementing default inheritance hierarchies, and a PFM (Paradigm Functional Morphology) Web site that allows the user to build and debug PFM theories.  Analytical tools are centered around plats (charts of the paradigms of all inflection classes for a given language); these tools derive principal parts and related measures from the plats. read more

Decision Making

Decision-Theoretic Academic Advising

Researcher: Dr. Judy Goldsmith

During the course of a student's undergraduate education, many decisions are encountered which may impact short- and long-term academic success as well as relative enjoyment and (perceived) utility that are obtained by the student.  Human advisors help the student advisee make decisions that can have positive major effects on their educational experience.  The advisor's task is complicated by a potential lack of knowledge of the individual student's goals and preferences.  Further, the potential long-term effects of actions may not be obvious even to experienced academic advisors.

In order to deal with the difficulties ecountered in academic advising our research group is developing tools and methods for generating stochastic models of an academic domain, and for fast stochastic planning and generation of advice.  The project is divided into three areas: model construction, planning, and interface design.  The academic domain poses challenges in each of these areas.

Probabilistic Computational Social Choice

Researchers: Dr. Judy GoldsmithDr. Andrew Klapper, Nicholas Mattei

One of the most common preference aggregation methods--the one most familiar to Americans--is election by majority.  Other preference aggregation methods are not always recognized as such, for example, (sports) tournaments.  One can view a sports tournament as an election where the best team wins.  We can affect the outcome of a vote or tournament by voting and playing truthfully and to the best of our ability, etc, or by manipulating the aggregation process.

There are several methods by which aggregation schemes can be manipulated.  The most intuitive and well known is by influencing individual agents (through payments or other means).  In real-world systems, typically not everything (the influence, the vote, the result) is observable by the manipulator.  With this project, we focus on uncertain outcomes: What happens if the manipulator has acces only to probabilities of agents' responses to attempts to influence them?

We achieve this through new model methods for established problems which take into account an agent's uncertainty about aspects of aggregation procedures.  Once we have developed these new models, we study the complexity of lobbying and other influence methods in this uncertain world. 

Rheumatoid Arthritis Decision Aid

Researchers: Dr. Judy Goldsmith, Kristine Lohr, MD, Paul Mihail

Rheumatoid arthritis (RA) is a serious disease, both painful and life-altering.  Sufferers often find themselves unable to perform basic tasks, including dressing themselves, opening containers, using silverware, or rising from a chair.  There are medications available that, in many cases with high probability, can enable the RA patient to accomplish such tasks.  However, these medication often have low-probability but scary side effects.  Patients often choose not to take drugs because of highly unlikely scenarios.

Although clinicians tell patients the probabilities of side effects, it seems that the patients do not grasp the unlikelihood of those possibilities.  We propose a decision support system to help them understand probabilities of effects and side effects of RA drugs by "experiencing" them in a computer-game-like setting

The proposed system will allow patients to view and manipulate an avatar that suffers a similar level of RA, and can choose to be treated with the drugs the patient is considering.  The system will run simulations of every-day tasks, showing multiple windows with varying levels of success.  The levels will be determined by the patient's disease level, the choice of treatment (for the avatar), and the known probabilities of efficacy and side effects. 

Web-based Interactive Organic Chemistry Homework

Researchers: Dr. Raphael Finkel, Dr. Robert Grossman (Chemistry)

ACE (Achieving Chemistry Excellence) is a web-based suite of programs for interactive chemistry homework.  It follows the pedagogic principal that students learn best by working problems, but that they should not be shown a "correct" answer unless they have completely worked it out themselves.  ACE provides a wealth of questions in Organic Chemistry that an instructor can assemble into assignments and examinations.  The author of each question (perhaps the instructor of the course) provides a seriesof evaluators that check for aspects of the student response.  The first evaluator that matches the response triggers both a score (on a 0-1 scale) and feedback.  It the response is incorrect, the feedback aims to show the student in what way the response is wrong, not what the right answer might be.  ACE currently has question types involving chemical structures, Lewis structures, mechanisms, multi-step synthesis, orbital energy diagrams, reaction coordinate diagrams, and more.  Our current efforts are to expand the framework to include questions specific to other disciplines.  read more

The video to the right provides a demonstration of ACE capabilities.


Researcher: Dr. Jane Hayes

The TraceLab Project seeks to develop an experimental workbench for designing, constructing, and executing traceability experiments, and facilitating the rigorour evaluation of different traceability techniques.  TraceLab is similar in some respects to existing tools such as Weka, MatLab, or RapidMiner, except that it is highly customized to support rigorous Software Engineering experiments as opposed to general data mining ones.  read more

The video to the right describes TraceLab and provides a short demonstration of its use.


Researcher: Dr. Jane Hayes

REquirements TRacing On target (RETRO.NET) is a tool developed by the software research group at UK to assist in the generation of traceability matrices between textual software engineering artifacts.  For more information, contact Dr. Hayes at

The demonstration to the right provides a quick overview of the tool and its capabilities.

Efficient Algorithms for Functions with Infinitely-Many Variables

Reseacher: Dr. Grzegorz Wasilkowski

There are many computational problems dealing with functions of infinitely many variables.  Such problems appear in, e.g., quantum chemistry and physics, financial mathematics, statistics, stochastic differential equations, and partial differential equations with random coefficients.  Actually, many problems involving stochastic processes arre examples of such ∞-variable problems.

Currently available methods are very inefficient, and new algorithms need to be found.  In this research project, we study a new family of methods, called Changing Dimension Algorithms.  These algorithms allow us to approximate or integrate functions with infinitely many variables at the cost polynomial in ε, where ε is the error demand.