Objectives:
Pan-tilt-zoom
cameras are dynamic in the sense that they provide very high resolution at
widely separated points of interest. Naturally, using deep zooming implies narrowing
the field of view. However, one may reason that target tracking allows
predicting motion, and prediction may save attention for detecting other
targets. In other words, scheduling points of interest can be a mitigating
factor, effectively allowing pan-tilt-zoom cameras to approximate
omni-awareness.
Considering
an urban environment observed by a number of pan-tilt-zoom cameras, the main
objective consists in automating the cameras to work in a cooperative manner to
track a number of targets (e.g. vehicles or people). This project is based in
the research and development of two fundamental components: (i) pan-tilt-zoom camera modeling and (ii) developing an
algorithm for assigning tasks to the cameras such that vision based
multi-target tracking has optimal performance.
Requirements (grades,
required courses, etc):
Interest
in the problem of visual target tracking
Localization:
ISR
/ IST
Observations:
Previous
works conducted at ISR/IST provide good starting points for the thesis. In
particular a number of software prototypes already exist for target detection,
tracking and camera scheduling.
More information:
http://users.isr.tecnico.ulisboa.pt/~jag/msc/msc_2017_2018.html