Multimedia Processing and Computer Vision
Research Areas
The Multimedia Processing and Computer Vision laboratory is widely known as one of the best of its kind in the UK and has also earned international recognition. Its work has involved collaboration with industrial partners and academics from UK and abroad. Its ongoing research covers a broad spectrum of computational techniques associated with visual and audio media, from video compression to medical image processing.
A particular feature of our work over in past 25 years has been the use of multiresolution signal representations. These include wavelets and related transforms for compression and segmentation and 'coarse-fine' methods for estimation of disparity fields in such areas as stereopsis and visual motion.
We have collaborated with many other research groups within the University of Warwick, including the Mathematics Institute and the Departments of Statistics and Psychology, University Hospitals of Coventry and Warwickshire and at other Institutions, including Yale, Harvard, Zurich and Bristol Universities, the Institute of Psychiatry and organisations such as Oxford GlycoSciences Ltd, Sony Broadcast and Professional (Europe), DERA Malvern (now QinetiQ) and the Forensic Science Service. Recently we have been involved in several projects with Warwick Medical School, Pattern Analytics Ltd, and Jaguar Land Rover research.
Faculty members*
Prof Chang-Tsun Li (now at Deakin University, Melbourne)
Dr Thomas Popham (School of Engineering)
You can find more information about our research work and our publications on the individual member pages.
Research Students
Jun Wang - Radiology image captioning and report generation
Saif Anwar - Interpretable and explainable ML for transportation systems
Wenbo Wei - Panoptic segmentation
Kai Liang - Applications of SlowFast networks for predicting vehicle manoeuvres
Cristina Manoila - Knee disease modelling from MRI
Jack Adams - Explainable and robust deep ANNs
Tom Wood - Automatic Music Transcription
Ian Tu - Vehicle occupant state and monitoring using Computer Vision
Recent Members and Graduates
Dr Greg Watson - Person Re-Identification (Senior Teaching Fellow, Warwick)
Jamie Bayne - Optimizing vision algorithms for modern HPC systems
Matt Smith (Department of Statistics) - Convolutional Neural Networks, Sparse networks and Deep Learning
Dr Xin Lu - Scalable Video Coding (now Senior Lecturer, de Monfort University)
Dr Heechan Park - Affine Symmetric Image Modelling and Its Applications
Dr Thomas Popham - Multicamera surface estimation and Multicamera Scene-flow estimation (Associate Prof, Warwick)
Dr Qiang Zhang - Medical Image Analysis, Computer Aided Diagnosis, Segmentation and object parameterization using Part Based Models (Research Fellow, Oxford)
*Our founding member, Professor Roland Wilson sadly passed away in November 2019. You may read about his life and wonderful contribution to the work of our research group here.
Images below link through to publications...
