|
PUBLICATIONS
|
 |
Bibliographies
|
 |
0
|
 |
 |
Book chapters
|
 |
0
|
 |
 |
Book reviews
|
 |
0
|
 |
 |
Books
|
 |
0
|
 |
 |
Books, edited
|
 |
0
|
 |
 |
Conf. papers
|
 |
0
|
 |
 |
Conf. presentations
|
 |
0
|
 |
 |
Conferences
|
 |
0
|
 |
 |
Discussion groups
|
 |
0
|
 |
 |
Grants
|
 |
0
|
 |
 |
Journal articles
|
 |
0
|
 |
 |
Periodicals/series
|
 |
0
|
 |
 |
Proceedings
|
 |
0
|
 |
 |
Proceedings, papers
|
 |
0
|
 |
 |
Reports
|
 |
0
|
 |
 |
Special issues
|
 |
0
|
 |
 |
Theses
|
 |
0
|
 |
 |
Treaties
|
 |
0
|
 |
 |
Working papers
|
 |
0
|
 |
|

|
STATISTICS
|
 |
Citation Rank
|
 |
|
 |
 |
Total Citations
|
 |
0 |
 |
 |
Publications
|
 |
0 |
 |
 |
Rank
|
 |
325637 |
 |
 |
Viewers
|
 |
4 |
 |
 |
Views
|
 |
1236 |
 |
|
|
 |
 |
Dr. Terry Caelli
(b. ----,
d. ----)
|
( Prev | Next )
|
 |
|
|
|
POSITION(S) / JOB TITLE(S):
|
|
Professor |
|
|
In general, my interests lie in the development of Computer Assisted Perception and Action Systems which use sensing, signal processing and Artificial Intelligence techniques. Currently I am working on two main projects:
(1)Environmental Monitoring Systems.
This work is concerned with the development of intelligent sensing systems for aiding the monitoring and intepreting spatio-temporal data sensed from active or passive sensors. Our two main projects in this area are: (a) the development of computer assisted Forestry Inventory systems from aerial cameras and other sensors; (b) the development of integrated GPS/GIS systems for monitoring human and animal behaviour in natural environments. Of particular interest is temporal GIS, how to integrate wavelet decompositions with a variety of hidden Markov models to attain efficent and accurate recognition and tracking algorithms.
(2) Measuring, recognizing and predicting complex human actions.
This work is concerned with training machines to learn how to describe, recognize and predict complex human skills and transfer such skills to others. Here we use both cameras and active sensors to obtain 3D movement information. Our specific interests lie in some new methods for describing actions in terms of the curvature-torsion traces of limb segments, wavelet decompositions, and the use of Dynamical Bayesian Networks, including Hierachical, Coupled Hidden Markov Models, to describe and predict such perception-action tasks.
|
|
|
Professor |
|
Computing Science |
|
University of Alberta |
|
|
Only Visible to Members of getCITED
|
|
|
Doctorate
|
|
|
University of Newcastle
|
|
|
Male / English
|
|
|
Unknown |
|
|
1107-2036
(Last changed on
2003/04/27 19:03:04)
|
|
  |
|
|
|
|