Details of Grant 

EPSRC Reference:	GR/J86322/01
Title:	CONTEXT BASED VISION
Principal Investigator:	Sullivan, Professor G
Other Investigators:	Baker, Professor K
Researcher Co-Investigators:
Project Partners:
Department:	Computer Science
Organisation:	University of Reading
Scheme:	Standard Research (Pre-FEC)
Starts:	01 June 1994	Ends:	30 November 1996	Value (£):	236,849
EPSRC Research Topic Classifications:	Image & Vision Computing
EPSRC Industrial Sector Classifications:	No relevance to Underpinning Sectors
Related Grants:
Panel History:
Summary on Grant Application Form
(i) To extend an existing system for traffic surveillance to use active models(ii) To investigate methods for classifying parameterised vehicle models.(iii) To develop an effective control strategy for arbitrating between vision modules.Progress:Objective i) has been fulfilled: An initial demonstration of the basic technique of using a force model to refine the pose of an hypothesised object was shown at ECCV94; this described a spring and smooth rods model, which led to an iterative solution of the pose parameters. A revised approach, which allows a direct solution of the pose parameters has also been demonstrated, and a paper has been submitted to an IEEE workshop being held in conjunction with ICCV95.Objective (ii) has also been explored and successfully demonstrated, though further work is needed to chart out its limitations. A University-supported PhD student (J M Ferryman) joined us in May 1994. Under instruction from Dr Worrall he developed a parameterised vehicle model using our existing modelling techniques, and built an interactive tool for recovering the parameters of vehicle instances. These data have been reduced using PCA to create deformable model of vehicle sub-classes (saloon, hatchback, estate cars) each controlled by 6 shape parameters, which account for the variation of vehicle instances within a subclass. The direct pose refinement technique (Objective (ii)) has recently been extended to derive the shape parameters automatically from selected images. A paper outlining the method has been submitted to IRS95, and fuller papers on these developments are in preparation for submission to BMVC95. Equipment money has been spent on upgrades to our existing SUN workstations. Plans are in place to upgrade one of the workstations further to use 4 sparc CPU modules, in order to provide a testbed for work towards Objective (iii).
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.rdg.ac.uk