this purpose i
we work on automated algorithms for image understanding and were specifically looking at trying to
understand images of outdoor scenes
we collect images from lots of different types of cameras be they web cams that
we can download images from or images that are uploaded to social network sites and
we write algorithms to try to interpret the images
we solve a number of different kinds of problems so one of the problems might
be given the set of images what is the three d geometry in the scene
or what are the material properties of the things in the scene or if we
have images captured over a longer period of time it might be something like howard
the plants growing in this scene or how is the weather changing from data one
of the things we're focused on right now is trying to use what is typically
been considered a nuisance
for outdoor scene understanding and try to use it to our advantage clouds moved to
outdoor scenes they cause various lighting changes and on partly cloudy days you have lighting
that gets brighter or darker brighter or darker that causes lots of trouble for algorithms
that are trying to say to recognize if something is changed so what we're trying
to do is
flip that on its head and say how can we actually use the fact that
it's a cloudy day to infer things about the scene and the camera so trying
to use clouds moving to the scene to estimate three d geometry
of what we're looking at trying to estimate what direction the cameras looking trying to
characterize the types of clouds that are passing through the scene we take large sets
of images and we try to extract patterns and they can be patterns that we
used understand the patterns themselves or patterns that we used to understand
things about the camera for the location that were in so we're really interested in
trying to take
video of the outdoor scenes and understand how people are moving through then how the
way that people move through an outdoor scene changes based on various other conditions
so for example there are more people walking around the u k campus on a
monday then there are on a sunday in general because people are walking classes and
are not on the weekends
and those are very simple patterns but they're also more complex patterns we want to
characterize how normal
the motion of people is on a particular day and how normal what people look
like use of a particular day as the search starts from you moving around the
world and seeing things to collecting some data and then trying to get things to
work
on that data to solve a problem and so we write code to try to
create this pipeline from source data to this target we're trying to get to
and we see how it works and then we iterate so we really have a
nice collection of different people working in this or different stages of their education we
can have people to make significant contributions at
all of these different levels
we have undergrads we're working on different ways to collected and different ways to visualise
it and to interact with it
and then we have phd students were doing things like let's take this sort of
images and let's build some machine learning for computer vision based approach to extract information
there's a world out there that's changing in sometimes predictable ways sometimes unpredictable way so
we want somehow
combine all of this together and build algorithms that can somehow take advantage of these
patterns are in the world
i
modeling