rut_washlogo

Acoustic Imaging &
Computer Visualization of Seafloor
Hydrothermal Flow

  TEAM
COVIS
PROJECTS & PROPOSALS
SOFTWARE & DATA
PUBLICATIONS
RELEVANT SITES
NEWS & RESEARCH


                                                 Feature Tracking

Vizualizing and analysing 3D time varying datasets (4D datasets scalar/vector) is very difficult because of the immense amount of data to be processed and understood. These datasets contain many evolving amorphous regions, and it is difficult to observe patterns and visually follow regions of interest. An essential part of the scientific process is to identify, quantify and track important regions and structures (objects of interest). This is true for almost all disciplines since the crux of understanding the original simulation, experiment or observation is the study of the evolution of the "objects'' present. Some well known examples include tracking the progression of a storm, the motion and change of the "ozone hole'', or the movement of vortices shed by the meandering Gulf stream. What is needed is visualization, quantification and querying techniques to help filter and reduce the data to a form more conducive to analysis. This is complementary to the standard visualization and helps explain in more mathematical and quantitative detail what is being seen.

Feature Extraction and Tracking is a big part of this process. Once features are identified, properties of the features and their evolutionary history can be computed. Finally, the tracking information and quantitative information can be used to enhance the visualization of 3D time-varying datasets. The information computed from feature tracking is in the form of meta-data, and can be used for data mining. We have developed a feature extraction and tracking paradigm for 3D time varying datasets. This paradigm is shown below.

                                       featuretracksteps

The first step is to extract features. Once the features are extracted and isolated, they can be tracked, quantified (measured). With these measurements, enhanced visualization are possible. Both stationary features and temporal-features (i.e. events) can be categorized and stored in a database for future searches (event querying, for example: Does a particular event occur in a large time-varying simulation?).

            featuretrackdetail

A full feature extraction and tracking system was developed. The programs allow a user to extract features from a 3D scalar dataset and then track those features over time. The code + user interface has been incorporated into Advanced Visual Systems (AVS) and Vis5D.The GUI of the AVS has been fully utilized to give the user complete access to all the parameters in order to control the feature tracking process. We also have a VTK gui available. This program only displays previously extracted features

If you are interested in trying the Feature Tracking Application please proceed to the "SOFTWARE & DATA" tab and e-mail: Karen Bemis (bemis@rci.rutgers.edu) or Jay Takle (jaytakle@eden.rutgers.edu)

 

© RUTGERS, The State University of New Jersey. All rights reserved.