0:00:07this purpose i
0:00:13we work on automated algorithms for image understanding and were specifically looking at trying to
0:00:18understand images of outdoor scenes
0:00:21we collect images from lots of different types of cameras be they web cams that
0:00:26we can download images from or images that are uploaded to social network sites and
0:00:31we write algorithms to try to interpret the images
0:00:34we solve a number of different kinds of problems so one of the problems might
0:00:38be given the set of images what is the three d geometry in the scene
0:00:42or what are the material properties of the things in the scene or if we
0:00:47have images captured over a longer period of time it might be something like howard
0:00:52the plants growing in this scene or how is the weather changing from data one
0:00:57of the things we're focused on right now is trying to use what is typically
0:01:01been considered a nuisance
0:01:02for outdoor scene understanding and try to use it to our advantage clouds moved to
0:01:06outdoor scenes they cause various lighting changes and on partly cloudy days you have lighting
0:01:12that gets brighter or darker brighter or darker that causes lots of trouble for algorithms
0:01:16that are trying to say to recognize if something is changed so what we're trying
0:01:20to do is
0:01:22flip that on its head and say how can we actually use the fact that
0:01:25it's a cloudy day to infer things about the scene and the camera so trying
0:01:30to use clouds moving to the scene to estimate three d geometry
0:01:34of what we're looking at trying to estimate what direction the cameras looking trying to
0:01:40characterize the types of clouds that are passing through the scene we take large sets
0:01:45of images and we try to extract patterns and they can be patterns that we
0:01:50used understand the patterns themselves or patterns that we used to understand
0:01:55things about the camera for the location that were in so we're really interested in
0:02:00trying to take
0:02:02video of the outdoor scenes and understand how people are moving through then how the
0:02:07way that people move through an outdoor scene changes based on various other conditions
0:02:13so for example there are more people walking around the u k campus on a
0:02:19monday then there are on a sunday in general because people are walking classes and
0:02:23are not on the weekends
0:02:24and those are very simple patterns but they're also more complex patterns we want to
0:02:28characterize how normal
0:02:31the motion of people is on a particular day and how normal what people look
0:02:35like use of a particular day as the search starts from you moving around the
0:02:39world and seeing things to collecting some data and then trying to get things to
0:02:43work
0:02:43on that data to solve a problem and so we write code to try to
0:02:48create this pipeline from source data to this target we're trying to get to
0:02:54and we see how it works and then we iterate so we really have a
0:02:56nice collection of different people working in this or different stages of their education we
0:03:02can have people to make significant contributions at
0:03:06all of these different levels
0:03:07we have undergrads we're working on different ways to collected and different ways to visualise
0:03:12it and to interact with it
0:03:13and then we have phd students were doing things like let's take this sort of
0:03:17images and let's build some machine learning for computer vision based approach to extract information
0:03:24there's a world out there that's changing in sometimes predictable ways sometimes unpredictable way so
0:03:30we want somehow
0:03:31combine all of this together and build algorithms that can somehow take advantage of these
0:03:37patterns are in the world
0:03:40i
0:03:49modeling