Date:
-
Location:
MDS 220
Refreshments: MDS 312, 3:30-4:00 pm
Title:
Collaborative Tracking and Robust Dictionary Learning Using Sparse Representation
Abstract:
In this talk, I will first present a robust, fast and accurate 3D
tracking algorithm: Prediction Based Collaborative Trackers (PCT). In
PCT, a novel one-step forward prediction is introduced to generate the
motion prior using motion manifold learning. Marginal space learning
based boosting is used to speed up both the training and testing
procedures. PCT is completely automatic and computationally efficient.
It requires less than 1.5 seconds to process a 3D volume which contains
millions of voxels.
Although PCT can be used to track the 2D/3D object accurately and
rapidly, it is not online updated. We have developed a robust online
learning based tracking algorithm using a local sparse appearance model
(SPT). A novel sparse representation-based voting map and sparse
constraint regularized mean-shift are fused for adaptive object tracking
through online learning.
In this talk, I will also introduce a novel dictionary learning algorithm
with a locally constrained sparse representation, called K-Selection. I
will also cover part of our ongoing research in developing a novel and
robust K-selection (RKS) dictionary learning algorithm which is not only
sparse but robust to outliers. These general algorithms are demonstrated
for tracking, background substractiona and recognition, and can be used
for statistical analysis as well
Files:
colloquium flyer- Dr. Yang (Feb 3).pdf
(118.33 KB)