Research

1. Face Related Projects

Over the past several years, we have developed various facial technologies. They include face detection and tracking, eye detection and tracking, gaze tracking, 3D face pose tracking, facial feature detection and tracking, facial expression analysis, facial action analysis, and face recognition...

2. Probabilistic Reasoning Using Graphical Models

In probabilistic graphical models, we have significant experience in developing theories for graphical model learning and efficient inference for different graphical models including Hidden Markov Models, Conditional Random Fields, Dynamic Bayesian Networks, and the Influence Diagrams. In graphical model learning, we have developed algorithms for learning the model parameters and structure, and learning the model under incomplete training data with qualitative constraints. For inference, we focus on developing methods that can perform efficient and timely inference by factoring out the common computations and by identifying the most informative evidences to use. We are also developing a unified probabilistic framework based on combining the directed and undirected graphs to produce a more expressive framework that can capture heterogeneous knowledge at different levels of abstraction...

3. Human Activity Modeling and Recognition

The Intelligent Systems Laboratory at RPI has long performed research related to human activity modeling and recognition. Specifically, we have performed research in face detection and tracking, human detection and tracking, human activity modeling and recognition. These efforts have led to algorithms and software for real time multi-view face detection and tracking, multi-target human body detection and tracking, human action and facial activity recognition.

4. Knowledge Augmented Visual Learning

5. Body Pose Estimation and Tracking

6. Real-Time Non-invasive Human State Monitoring and Recognition

Our work in this area focuses on three aspects: 1) developing the non-intrusive and real time sensing techniques (vision sensors and physiological sensors)for extracting various features typically characterizing the state of the user; 2) develop a probabilistic framework based on the Bayesian Networks to systematically integrate various sensory measurements to produce a composite index characterizing user's state; 3) determining the optimal assistance to provide to user in order to maintain user productivity and performance...

7. Brain Computer Interface (BCI)

Our research in BCI focuses on developing advanced machine learning techniques for brain signal classification, decoding and prediction. We are particularly interested in developing probabilistic graphical model to characterize the signal progression pattern in space and time. This approach not only provides an intuitive interpretation for spatio-temporal relationships among different brain areas, but also captures the temporal variation within brain signals, which is not considered sufficiently in conventional methods.

8. Image Segmentation and Medical Imaging

9. Active Information Fusion for Decision Making Under Uncertainty

The goal is to develop a unified probabilistic framework for effective representation of sensor data of different modalities, for active fusion of sensory data, and for efficient and timely decision-making....

10. More Projects