Events Calendar

PhD Defense - Jan Prokaj

Ph.D. candidate: Jan Prokaj
Time: 4:00pm to 5:30pm, April 19, 2013
Location: GFS104
Committee:
Gerard Medioni (chairman)
Ramakant Nevatia
Shrikanth Narayanan
Title: Exploitation of Wide Area Motion Imagery

Abstract:

Current digital photography solutions now routinely allow the capture of tens of megapixels of data at 2 frames per second. At these resolutions, a geographic area covering a whole city can be captured at once from an unmanned aerial vehicle (UAV), while still allowing the recognition of vehicles and people (for sensors under development). This fact, in tandem with the availability of increased computational power, has led to the growth of wide area motion imagery (WAMI).

Our objective is to develop algorithms that automatically process the imagery of interest and turn it into a more useful, informative form. This more informative form can exist at different levels of semantics, from low-level to high-level. Therefore, the set of algorithms we propose operates in range from low-level processing to high-level processing.

WAMI data is often captured by an array of cameras. Therefore, at the lowest level, we need an algorithm that takes an array of individual camera images and estimates a high quality mosaic. We propose a piecewise affine model to handle all image deformations that deviate from the standard pinhole camera model.

The next level of processing involves estimating the trajectories of all moving objects, or ``tracking.'' We propose a tracking algorithm that optimally infers short tracks using Bayesian networks. These tracklets are then integrated into a multi-object tracking algorithm that achieves good performance on aerial surveillance video. When coupled with a regression-based tracker, stopping targets can be handled.

WAMI is often collected over urban areas, where there are tall buildings, and other structures, which cause severe occlusion that in turn causes significant track fragmentation. To solve this problem, we propose a method which links fragmented tracks using known 3D scene structure.

In order to enable large scale semantic analysis of WAMI data, higher level algorithms that determine at least some of the semantics are necessary. We propose a framework based on the Entity Relationship Model that is able to recognize a large variety of activites on real data as well as GPS tracks.

When very high resolution data are available, such as from high-definition cameras on the ground, we want to infer even more semantics from video data. Under these circumstances, we propose an algorithm for vehicle classification that works with arbitrary vehicle pose.

Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 104

Audiences: Everyone Is Invited

Contact: Lizsl De Leon