Sensor Integration and Data Fusion

There are no current dates for this course. If you want to register your interest please contact Barbara Steel on

Please note that the following details are provisional and will be updated


Data fusion enhances the performance of many decision-making procedures by synergistic use of information provided by multiple sources. The interdisciplinary nature of data fusion makes it a very powerful technique with applications to industrial inspection, remote sensing and military surveillance, robotics, medical diagnosis and even financial market analysis. This course is intended for professionals with an engineering/science background wishing to exploit data fusion principles for solving decision-making problems in their fields.




Time Day 1 Day 2 Day 3
Introduction to Data Fusion 
Dr T Windeatt
Characteristics of Sensors 
Professor M J Underhill
Fundamentals of Image Processing Pattern Recognition 
Professor M Petrou
Statistical Decision Rules 
Electromagnetic Sensors 
Professor M J Underhill
Pattern Recognition 
Professor J Kittler
Distributed Detection Networks 
Infrared Sensors and Lasers 

Professor M J Underhill

Feature Level Fusion 

Professor J Kittler

Neural Computing 
Dr T Windeatt
Sensor Integration 

Professor M J Underhill

Decision Level Fusion 

Professor J Kittler


Day 1
· Data fusion models.
· Bayesian inference for data fusion.
· Estimation theory.
· Measures of data association.
· Elements of detection theory.
· Distributed Bayesian and sequential detection.
· Measures of performance based on decision theory
· Data fusion for non-destructive testing.
· Applications to target classification and  multi-sensor multi-target tracking.

Day 2
· Sensors used in data fusion.
· Optical sensors.
· Radar.
· Infrared sensors.
· Ultrasonic sensors.
· Sonar. Laser.
· X-ray.
· Characteristics of sensors in the time and frequency domains.
· Effects of nonlinearities.
· Accuracy and calibration errors.
· Sensor signal conditioning and processing.
· Sensor management and integration.

Day 3
Pattern recognition and classification.
· Feature selection and extraction.
· Co-operating classifiers.
· Cluster analysis techniques.
· Introduction to neural computing and networks for data fusion.
· Data and decision function.
· Decision making in context.
· Co-operative decision networks.·


Professor Maria Petrou BSc, PhD has been working on Computer Vision since 1986, and has published more than 150 papers, examples of which are; Astronomy, Low Level Vision, Feature Extraction, Texture Analysis, Markov Random Fields, Remote Sensing, Industrial Inspection and Medical Signal Processing. She is a Professor at the University of Surrey and a member of the British Machine Vision Association, the Society of Optical Engineering and the IEEE. She is Associate Editor of IEEE Transactions on Image Processing, and edits the Newsletter of the International Association of Pattern Recognition.

Professor Mike Underhill MA, PhD, FEng, FIEE, FRSA joined the University in 1992 as Head of Department until 1996. His 31 years in industry encompassed 24 years at Philips Research Laboratories, 6 years as Technical Director of MEL-Philips and 1 year as Engineering Director of Thorn EMI Sensors. Since 1961 his activities cover HF Radio, EW, Radar and IR and he is continuing research in some of these areas. He holds about 50 patents in these areas and related fields - the latest being on phase noise and time jitter reduction.

Dr Terry Windeatt B.Sc. Applied Science (Sussex), M.Sc. ElecEng (California), B.A. Theology (CNAA),PhD (Surrey) has been working since 1990 in the fields of Computer Vision, Neural Networks and Machine Intelligence. Previously he spent eight years with General Motors and then Xerox in Research and Development. His industrial experience was gained while working in multi-disciplinary groups concerned with sensor modelling and simulation of intelligent machines. He worked on early versions of closed loop systems for car emissions control and for xerographic process control. His recent and current research projects include: understanding aerial imagery; solder paste printing and control; range data modelling; integrating multiple views; colour space modelling; pattern classification; constructive neural networks. He is a Chartered Engineer and member of the IEE.

Professor Josef Kittler is Director of the Centre for Vision, Speech and Signal Processing at the University of Surrey. He has more than 30 years of experience in pattern recognition, using both statistical and neural network approaches. He has worked on various theoretical aspects of Pattern Recognition and on many applications including System Identification, Automatic Inspection,
ECG diagnosis, Remote Sensing, Robotics, Speech recognition, Character Recognition, Document Analysis, Biometrics, Image and Video Retrieval and Computer Vision. He has co-authored a book ``Pattern Recognition: a statistical approach'' and  published more than 400 papers. He  is a member of the Editorial Boards of Pattern Recognition Journal, Image and Vision Computing, Pattern Recognition Letters, Pattern Recognition and Artificial Intelligence, Machine Vision and Applications, and Pattern Analysis and Applications.


Price per person, including lunch, refreshments and printed course notes
Enquiries should be addressed to: Barbara Steel, Course Co-ordinator    Tel: +44(0)1483 686040
Fax: +44(0)1483 686041 or send an email by clicking below:
Short Courses Enquiry
To reserve a place on the above course please complete this Registration Form

Please note that we cannot offer accommodation on site for this course. Click HERE for details of accommodation available in the Guildford Area.


The courses run by the CE office are also registered under the IEE CPD Scheme and formerly CPD units have been awarded for attendance, participation and assessment. From January 1999 the IEE introduced a new scheme by which "levels of competence" are assessed. The CE office will be bringing in a similar scheme in the near future which will relate to this. Please check our website for updated information on this.



Barbara Steel: last revised 24 June 2002