Computer Vision

Our recent work has focused on activity analysis from video, with fundamental research on categorisation, tracking, segmentation and motion modelling, through to the application of this research in several areas. Part of the work is exploring the integration of vision within a broader cognitive framework that includes audition, language, action, and reasoning.

Who we are

Professor, Lab Director
More
Associate Professor
More
Professor of Automated Reasoning
More
PhD Research Student
More
2:1
PhD Research Student
PhD Research Student
More
2:1
PhD Research Student

Research summaries

Learning appearance and language characteristics from TV shows for re-animating a talking head
More
Learning and predicting activities in an egocentric setup, applied to equipment workflow
More
Learning about the activities within a scene, and the objects involved in these activities
More
Carried object detection is applied using geometric shape properties and tracking is performed using spatio-temporal consistency between the object and the person
More
Learning about activities observed from a mobile robot
More
Synthesise an interactive agent by learning from the interactive behaviour of people
More
Resolving visual ambiguity by finding consistent explanations, applied to the detection of theft from bicycle racks
More
Detecting large objects (e.g. bags) carried by pedestrians from video
More
Learn about the objects and patterns of moves used in simple table-top games, and then apply these to play the game
More
Detecting atypical pedestrian pathways, assuming a simple model of goal-directed navigational behaviou
More
Enforcing global spatio-temporal consistency to enhance reliability of moving object tracking and classification
More
Modelling traffic interaction using learnt qualitative spatio-temporal relations and variable length Markov models
More
Detecting unusual events by modelling simple interactions between people and vehicles
More
Motion representations learning using a convolutional autoencoder with a sparsity constraint; and normality modelling and anomalies detection using one-class SVMs.
More
Learning and predicting activities in an egocentric setup, applied to equipment workflow
More