EPSRC logo

Details of Grant 

EPSRC Reference: GR/K44077/01
Title: DRIVA:AN INTEGRATED SYSTEM FOR THE CHARACTERISATION OF DRIVABLE REGIONS BY INTELLIGENT VISION AND ANALYSIS
Principal Investigator: Buxton, Professor BF
Other Investigators:
Researcher Co-Investigators:
Project Partners:
DSTL - JGS Pre Nexus Migration
Department: Computer Science
Organisation: UCL
Scheme: Standard Research (Pre-FEC)
Starts: 28 May 1996 Ends: 27 November 1998 Value (£): 205,364
EPSRC Research Topic Classifications:
Image & Vision Computing
EPSRC Industrial Sector Classifications:
Aerospace, Defence and Marine Environment
Creative Industries
Related Grants:
Panel History:  
Summary on Grant Application Form
The aim of the DRIVA project is to develop an automatic system for detecting and classifying the drivable regions in images of natural terrain. The system will be based on statistical machine vision techniques, in particular the active snake and point distribution models developed in the UK over the last few years, for detecting, tracking and modelling the appearance of objects by capturing the main properties of their shape, colour and texture and characteristic variations. Statistical snake techniques will first be used to develop a semi-automatic tool for the generation of training data which will be validated against imagery labelled by hand. This tool will then be used to generate a larger set of data for the training and refinement of the automatic system which will aim to use active snake and point distribution models for the detection and classification of drivable regions, including for example, their direction, the type and slope of the terrain, the presence of junctions etc. The automatic system will be evaluated in three main ways:+ by using images that have been independently labelled by hand in order to provide a quantitative comparison of the classification;+ against the performance of other techniques developed by the industrial collaborators and,+ by comparison with the performance of a human operator's annotation and driving commands from a graphical simulation. Performance criteria will be developed in collaboration with industrial end-users and long image sequences of 10-30 mins duration will be provided by one of the industrial collaborators (DRA Chertsey) for use in the above. An extension of the method for indicating longitudinal positional information in an agricultural application will be studied, the potential for applying such techniques to other types of more general outdoor imagery will be explored and the feasibility of hardware implementations assessed.
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: