EPSRC logo

Details of Grant 

EPSRC Reference: GR/S16980/01
Title: CONcurrent Hierarchical SENSor Registration and FUSion (CONSENSUS): Applications to seabed classification
Principal Investigator: Petillot, Professor Y
Other Investigators:
Researcher Co-Investigators:
Project Partners:
Inst of Marine Biology Of Crete (IMBC)
Department: Computing & Electrical Engineering
Organisation: Heriot-Watt University
Scheme: First Grant Scheme Pre-FEC
Starts: 21 April 2003 Ends: 20 January 2007 Value (£): 129,026
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
The primary aim of this proposal is to develop a joint registration and fusion scheme for highly multi-modal data sources of varying granularity. In most current techniques, the sources are first registered and then fused, the two processed being completely independent. Moreover, the registration of highly multi-modal sources is particularly difficult when using conventional techniques based on feature extraction and matching as the feature selection and matching is very problematic. We propose to develop a scheme where the registration is performed concurrently with classification. In the proposed scheme, the registration parameters are chosen to optimise the joint classification of the combined sources. The problem of registration-fusion is stated as the minimisation of the conflict between sources with respect to the registration transform. This project takes its origin in discussions with marine scientist. Today's sensing technology provides them with large amount of highly multi-modal data (sonar, video, bathymetric), with various degree of resolution. With more and more sonar data available covering large areas of the sea floor, a tool enabling to classify accurately these areas is critical for the offshore industry and the marine science community. The secondary objective of this program is to provide marine scientist with a tool for automated analysis of sea-bed data, a very important field were very little has been done so far. The techniques developped in this program could also easily be applied to other fields(Remore Sensing, Medical imaging) yielding even more benefits to the scientific comunity.
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.hw.ac.uk