Pavan
Turaga
Assistant
Professor
Arts Media and Engineering
Electrical, Computer, and Energy Engg.
Arizona State University |
|
|
|
Prospective
graduate students,
please see my research below, and if
interested please send me an email at pturaga@asu.edu with your resume.
|
|
About
Me
Hi,
I am
Pavan Turaga. I joined
in Fall 2011 as an Asst. Prof. jointly between the
departments
of and . I obtained my PhD in 2009 from the ECE
Department at the
University of Maryland, College Park
under the guidance of . I then spent two years
as a Research Associate at the Center for Automation Research,
UMD. My
broad
research interests are in the following areas
News
- 'Manifold-Precis'
paper accepted in
NIPS 2011.
- Diamond-Sentry
featured in
Older News
- Our
technology won the
- I
was awarded 2009's
- Selected
to
participate in the Workshop.
|
About
my Research
Humans
are surrounded with
signals and sensors of all kinds such as cell-phones, cameras, sensors
in automobiles, medical sensors, and ambient sensors. A large portion
of the signals recorded by these sensors is directly related to the
underlying activities, emotions, thoughts, and intents of humans. My
research agenda is to interpret these varied signals to reveal hidden
structure and meaning in them. These structures would then yield
methods to meaningfully organize what is already out there (e.g.
organizing Youtube videos), exploit the organized data to assign
meaning to new data (e.g. automatically tagging photos in personal
albums), and help humans in making critical decisions (e.g. medical
decision support). Toward this end, I envision the use of multiple
disciplines such as signal processing, computer vision, machine
learning, neuroscience -- and multiple technologies such as
crowd-sourcing, ambient intelligence, collaborative filtering
etc.
Some
of the projects that I have
worked on which involve some of the above ideas are listed below.
|
Some Selected Projects
|
|
| Geometric
and Manifold approaches for Blur Compensation |
A
fusion of image
formation models and geometric constraints on images and image-patches. |
 |
J. Ni, P.
Turaga, V. M. Patel, R. Chellappa, “Example-driven
Manifold priors for Image Deconvolution”, accepted at
IEEE Transactions on Image Processing 2011.
Z. Zhang,
E. Klassen, P.
Turaga, R. Chellappa, and A. Srivastava, “Blurring-Invariant
Riemannian Metrics for Comparing Signals and Images”,
accepted
at International Conference on
Computer Vision (ICCV) 2011. |
| Analyzing
and Organizing Consumer Video: Scenes and Human Activities |
Exploiting new cues such
as scene motion
and exemplar diversity for summarization and recognition. |
|
N.
Shroff,
P.
Turaga, and R. Chellappa. “Moving Vistas: Exploiting Motion
for
Describing Scenes”, at IEEE
conference on Computer Vision and Pattern
Recognition (CVPR), June 2010.
N.
Shroff,
P.
Turaga, and R. Chellappa, “Video
Precis: Highlighting Diverse Aspects of Videos”, at
IEEE Transactions on Multimedia, Dec 2010.
|
| Analytic Manifold
Models of Appearance and Motion |
Mathematical models for
linear dynamical
systems using Grassmann manifold interpretations.
|
 |
P. Turaga,
A. Veeraraghavan, A. Srivastava, and R. Chellappa.
“Statistical
Computations on
Grassmann and Stiefel manifolds for Image and Video-based
recognition”, in IEEE
Transactions on Pattern Analysis and Machine Intelligence (PAMI),
accepted 2010.
(Also
earlier CVPR paper
P.
Turaga and R. Chellappa. “Locally Time-Invariant models of
Human
Activities using Trajectories on the Grassmanian
”, at IEEE conference
on
Computer Vision and Pattern
Recognition (CVPR), June 2009.
|
| Knowledge
Extraction from Video |
Activity based
summarization: fusion of
human motion models, geometric invariance principles, and data mining. |
 |
P.
Turaga, A.
Veeraraghavan and R.
Chellappa, “Unsupervised
View and Rate Invariant Clustering of Video Sequences”, in Computer
Vision and Image
Understanding (special issue on Video Analysis), March 2009. .
P.
K. Turaga,
A.Veeraraghavan and R. Chellappa.
“From videos to verbs: Mining Videos for Activities using a
cascade of dynamical systems”, in IEEE conference on
Computer
Vision and Pattern Recognition (CVPR), June 2007. |
| Large Scale
Activity Recognition in Video and Sensor Networks |
Petri-Net based graphical
models for
sequential, synchronous and concurrent human actions. |
 |
P.
Turaga and Y. Ivanov, “Diamond
Sentry: Integrating Cameras and Sensors for Real-Time Monitoring of
Indoor Spaces”, accepted at
IEEE Sensors Journal, Special Issue on Cognitive Sensor Networks,
2010. .
M. Albanese,
V.
Moscato, R. Chellappa, A. Picariello, V. S. Subrahmanian, P. Turaga and
O. Udrea, “A Constrained Probabilistic Petri-Net Framework
for
Human Activity Detection in Video”, in IEEE Transactions
on Multimedia, December 2008.
A.
Sankaranarayanan, R. Patro, P. Turaga, A. Varshney, and R.
Chellappa, “Modelling and
Visualizing Human Activities for Multi-Camera Networks”, accepted
at EURASIP Journal on
Image and
Video Processing, 2009. |
|
