|
|
Salman Anwar
Khokhar Graduate Research
Assistant Computer Vision
Lab, UCF |
|
Publications: Similarity invariant classification
of events by KL divergence minimization, Salman Khokhar, Imran
Saleemi, Mubarak Shah, ICCV 2011. |
Short Bio:
|
I
am a second year PhD student at UCF working under the supervision of Prof. Mubarak Shah. Prior to joining UCF in
the Fall of 2010, I worked for year at University of Engineering and
Technology as a Lab instructor from where I also earned by BE degree
Electrical engineering in the Fall of 2009. |
Recent Research Projects:
Scene modeling using motion
patterns: PerSeas [2010-2012]
|
|
In this project we use track or optical flow data to
extract motion patterns from a scene which serve as descriptors of the
activity in the scene. These patterns are obtained by a hierarchical linking
of clusters of flow or tracking data. They can then be used to detect
anomalous behavior in traffic flow. |
Similarity invariant classification
of events by KL divergence minimization: PerSeas [2010-2012]
|
|
In this project we aim to
model events found in traffic scenes using motion patterns obtained from a
hierarchical clustering of optical flow. Two events are then compared by
warping them in such a way that their KL divergence is minimized. We
accomplish this using an iterative warping approach. After this a
dissimilarity score may be computed using KL divergence. Related publication , Project page, Presentation |
Contact:
·
Email: s”mylastname” ‘at’ eecs . ucf .
edu
·
Ph: 407 962 5895
·
Physical address: HEC 249, UCF, Central FL Blvd,
Orlando, FL, 32816, USA.