Our research interests revolve around theoretical modeling and experimental understanding of multi-instrument measurement systems that deal with multi-dimensional multi-variate data, as well as, around automation of common image pre-processing and analysis tasks. Based on our past work, our research could also be described as X-informatics, where the X stands for bio, hydro, medical image, or sensor.

Research Statement

Our research involves research and development of solutions to real life problems, often in collaboration with other scientists (in our terminology "domain" scientists) in the application areas of machine vision, synthetic aperture radar (SAR) target and scene modeling, land use and land cover classification, bio-informatics, microscopy and medical image processing, geo-spatial information systems (GIS) and advanced sensor environments. The work draws from theoretical foundations of image and video processing, computer vision, statistical modeling, data mining and pattern recognition, software engineering and sensor design.

The main goal of our research and development is to automate information processing of repetitive, laborious and tedious analysis tasks and build user-friendly decision-making systems that operate in automated or semi-automated mode.

Peter Bajcsy

ISDA Group leader and Research Scientist, NCSA
Adjunct Professor of Electrical and Computer Engineering
and Computer Science Departments
Associate Director for Data Analytics and Pattern Recognition,
Institute for Computing in Humanities, Arts and Social Science (I-CHASS)

1. CyberInfrastructure environments: Workflow environments, provenance information gathering.
   • Understanding Computational Requirements of Preservation and Reconstruction.
   • Lowering Adoption Barriers of Workflow Systems.
2. Document analysis: Image and text extraction and pre-processing, image and text information aggregation, information classification and knowledge repository building, document clustering. Optical character recognition from paper forms. Automated detection of regions of interest.
   • ECHO: A System for Fighting Childhood Obesity with Screening, Intervention and Tracking.
   • Bicentennial celebration of Abraham Lincoln's birth.
3. Intelligent spaces: Hazard sensing: Wireless sensor communication; Spectral sensor registration and calibration; Multi-sensor data fusion; Collaborative robot control for sensor deployment; Spatially adaptive hazard sensing;
   Tele-immersive Environments:
   • Remote Dance.
   • Remote Wheelchair Basketball Coaching.
   • GroupScope - Supporting Social Science Research.
4. Multi-spectral and hyper-spectral analysis and modeling: Raster and vector data processing; Feature extraction and selection from high-dimensional data; Statistical, model-based and hybrid scene analysis and synthesis.
   • Multi-sensor Multi-spectral Scene Modeling.
5. Medical and bioinformatics data: 3D reconstruction from 2D confocal microscopy imagery; Microarray data analysis; Data integration of 3D multi-modal data: MRI, DTI, histology;
   Understanding Medical and Bio-informatics Data:
6. Data mining of large size datasets with geospatial information: Integration of remote sensing, airborne imagery and ground measurements.
   Geospatial information systems: Integration of raster, vector and tabular data with georeferencing information, uncertainty analysis of integration;
   Large datasets with geospatial information:
   • Learning from Geospatial Data, GeoLearn software.
   • Algal Biomass Prediction.
   • Groundwater Recharge And Discharge Estimation.
   • Costa Rica 2050

All (current and past) projects

Main page
  Image To Learn (Im2Learn)
  CyberIntegrator
  Spatial Pattern To Learn (SP2Learn)
  Image Provenance To Learn (IP2Learn)
  Geospatial Image To Learn (GeoLearn)