Tracking and Behaviour Modelling

finding new ways to represent, learn and apply visual models of behaviour

Our research on the visual analysis of behaviour has focussed largely, but not exclusively, on human behaviour. We are interested in all aspects of this problem, including fundamental research on categorisation, tracking, segmentation and stochastic modelling, through to applied work addressing social and commercial priorities. Some of our recent work, in collaboration with the School's KRR group, is exploring the integration of vision within a broader cognitive framework, including audition, inductive reasoning, and intentionality.

	Protocol learning Learning games from observation
	Learning about activities from video A new EPSRC funded project to investigate unsupervised learning of activities from video.
	Detecting Carried Objects Detecting carried objects in short video sequences
	Watermark Extraction Paper-based Watermark Extraction with Image Processing
	Intentionality Using psychological ideas of intentionality and goal-directedness within behaviour modelling
	Temporal Continuity Enforcing global spatio-temporal consistency to enhance reliability of moving object tracking and classification
	Traffic Interactions Modelling traffic interaction using learnt qualitative spatio-temporal relations and variable length Markov models
	Car Tracking A generic object tracker, demonstrated tracking vehicles
	Music via Motion Creating an augmented and interactive audio-visual space
	Synthetic Interaction Synthesising an interactive agent by learning from the interactive behaviour of people
	Soccer Tracking Tracking the movements of individual players in team games
The projects shown below have been undertaken in Leeds, some time ago now, but are still of interest. Please follow the links below to find out more...
	Electronic stockman's eye Tracking cows and looking for abnormalities in their movements
	VLMMs of behaviour Learning variable length markov models of human behaviour
	IMV Detecting unusual events by modelling simple interactions between people and vehicles
	OMR Optical music recognition (with dept. of music)
	Behaviour modelling Modelling of `object behaviours' using detailed, learnt statistical models
	Hand tracking Robust, model-based methods for tracking deformable objects
	Pedestrian tracking Contour tracking using Active Shape Models. Source code for the Baumberg tracker.