Multiple object tracking using graphical models

Roslyn Lau (ANU)

COMPUTER VISION AND ROBOTICS SERIES HDR Monitoring

DATE: 2012-08-23
TIME: 16:00:00 - 17:00:00
LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU
CONTACT: JavaScript must be enabled to display this email address.

ABSTRACT:
Multiple object tracking is the process of estimating the number and state (e.g., position and velocity) of multiple objects given a sequence of noisy measurements. That is, multiple object tracking answers questions such as "how many objects are there?" and "where are they located?" by processing measurements collected over time.

In this HDR monitoring presentation, recent work on group object tracking, where the motion of the objects are correlated, will be discussed. The talk includes sparse approximations for the group object tracking problem and separately mentions variational inference methods being researched for the problem.

BIO:
Roslyn Lau is a PhD candidate in the Research School of Computer Science, ANU.