[Colloquium] FW: Guest Speaker Announcement
Ponda Barnes
pondabarnes at tti-c.org
Tue May 22 14:57:26 CDT 2007
REMINDER!!
Guest Speaker
Presented by: Toyota Technological Institute at Chicago
Speaker: Greg Mori
Speaker's home page: http://www.cs.sfu.ca/~mori/
Date: Thursday, May 24, 2007
Time: 10:00 am
Location: TTI-C Conference room
Title: Detecting Pedestrians by Learning Shapelet Features and Boosted
Multiple Deformable Trees for Parsing Human Poses
Abstract:
In this talk, we present two pieces of work in the "Looking at People"
domain. In the first part, we address the problem of detecting pedestrians
in still images. We introduce an algorithm for learning
shapelet features, a set of mid-level features. These features are focused
on local regions of the image and are built from low-level gradient
information that discriminates between pedestrian and
non-pedestrian classes. Using AdaBoost, these shapelet features are created
as a combination of oriented gradient responses. To train the final
classifier, we use AdaBoost for a second time to select a subset of our
learned shapelets. By first focusing locally on smaller feature sets, our
algorithm attempts to harvest more useful information than by examining all
the low-level features together.
We present quantitative results demonstrating the effectiveness of our
algorithm. In particular, we obtain an error rate 14 percentage points
lower (at $10^ {-6} $ FPPW) than the previous state of the art
detector of Dalal and Triggs on the INRIA dataset.
In the second part, we present a method for estimating human pose in still
images. Tree-structured models have been widely used for this problem.
While such models allow efficient learning and inference,
they fail to capture additional dependencies between body parts, other than
kinematic constraints. In this paper, we consider the use of multiple tree
models, rather than a singletree model for human pose
estimation. Our model can alleviate the limitations of a single
tree-structured model by combining information provided across different
tree models. The parameters of each individual tree model are trained via
standard learning algorithms in a single tree-structured model. Different
tree models are combined in a discriminative fashion by a boosting
procedure. We present experimental results showing the improvement of our
model over previous approaches on a very challenging dataset.
If you have any questions or would like to meet the speaker, please contact
Ponda Barnes at pondabarnes at tti-c.org
For future TTI-C talks and events, please visit
http://ttic.uchicago.edu/cal/month.php
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20070522/3620d866/attachment-0001.html
More information about the Colloquium
mailing list