Digital Imaging Research Centre

Vision Systems

Contents of this page - Introduction |CCTV in the Railways| CROMATICA Project | Sample Publications
 

Introduction

Our team works in two main activities:

• Video-based monitoring of pedestrians

• Asynchronous mechanisms for real-time systems

Pedestrian Monitoring

This refers to the use of video processing and computer vision techniques for the monitoring of pedestrians. In particular, we have targetted two aspects:

• Crowded conditions. 

• Public transport scenarios (mainly metropolitan railways) 

In this field, we have participated in national and international projects.

"Getting the Best Use out of CCTV in the Railways" (completed August 2003), funded by the Rail Safety and Standards Board (RSSB) and jointly carried out with Mott MacDonald and Ipsotek Ltd. This study was commissioned by the RSSB to examine the current and future use of CCTV in the railways, motivated by the theme of trespassing and vandalism. The overall aim was to understand the ways in which these systems are being used and, together with a detailed analysis of the current state-of-the-art in research and industrial systems, propose ways in which such use can be more effective. Public deliverables:

• "Executive Summary"
  
• "Existing CCTV Systems", Volume 1 (Information that was extrapolated from a combination of site surveys and a desktop study.  As a result of this review, a high-level synopsis of the current status of rail CCTV systems was produced, together with summary findings highlighting particular areas)
• "Existing CCTV Systems", Volume 2 (Contains the individual survey reports which provide more descriptive information related to the locations surveyed.  Additionally, it incorporates spreadsheets containing the data received from the postal questionnaire, which formed the basis of the desktop study).
• "New and Emerging Technologies" (Reviews of the state-of-the-art in academic research and industrial systems relevant to advanced CCTV systems for use in the railways).
• "Advanced CCTV Pilot Project Proposals" (A set of possible follow-on projects to assess the feasibility and potential impact of advanced CCTV systems in the railways).
• Final Presentation
  

CROMATICA: EU-funded, completed in March 1999. Development of enabling technologies (video-based detection, wireless transmission, etc.) to improve surveillance of passengers in public transport systems.

PRISMATICA: EU-funded, started April 2000 (for 36 months). Follow-up to CROMATICA. Improvement of personal security levels in public transport systems through integrated combinations of tools (technology) and processes (management, training, legal frameworks, etc.). Other useful links: Our PRISMATICA Web server

ADVISOR: EU-Funded, started January 2000 (for 36 months). Advanced data infrastructures for public transport systems, especially for CCTV monitoring. Advanced image interpretation techniques (tracking, camera handover, etc.).

PERSEC: EPSRC (UK's Engineering and Physical Sciences Research Council) funded project in collaboration with the Centre for Transport Studies, University College London. Started October 1999 for 30 months. Assessment of video/image processing techniques to improve personal security in public transport systems.

Asynchronous mechanisms for real-time systems

COMFORT: EPSRC-funded in collaboration with the University of Newcastle

COHERENT: EPSRC-funded in collaboration with the University of Newcastle

For further information, please contact

Dr. Sergio A. Velastin, School of Computing & Information Systems, Kingston Universtity, Penrhyn Road, Kingston upon Thames, Surrey, KT1 2EE, UK 
(Tel: +44 (20) 8547 7705, Fax: +44 (20) 8547 7972) 
 

Sample Publications

• Fuentes L.M., Velastin S.A. (2001), "People tracking in surveillance applications", 2nd IEEE International Workshop on Performance Evaluation on Tracking and Surveillance, PETS 2001, Kauai (Hawaii-USA), 14/12/2001

• Luis M. Fuentes and Sergio A. Velastin (2001), "Assessment of Image Processing as a means of Improving Personal Security in Public Transport", in Video-Based Surveillance Systems, Computer Vision and Distributed Processing, Paolo Remagnino, Graeme A. Jones, Nikos Paragios and Carlo S. Regazzoni Editors, Kluwer Academic Publishers, 2001, ISBN 0-7923-7632-3, Chapter 13, Pages 159-166.

• Fuentes L.M., Velastin S.A (2001), "Foreground segmentation using luminance contrast", 2001 WSES International Conference on Speech, Signal and Image processing, SSIP 01, 04/09/2001

• S.A. Velastin (2000): "Estimating pedestrian density in crowded conditions" [PowerPoint 97, 3.3MB] , BMVA Technical Meeting on Intelligent Visual Surveillance, 8th March 2000, London.

• B.A. Boghossian, S.A. Velastin (1999): “Image Processing System for Pedestrian Monitoring using Neural Classification of Normal Motion Patterns”, Measurement and Control, Vol. 32, Issue 9 (Special Issue on “Intelligent Vision Systems”), pp. 261- 264.

• B.A. Boghossian, S.A. Velastin (1999): “Motion-Based Machine Vision Techniques for the Management of Large Crowds”, IEEE 6th International Conference on Electronics, Circuits and Systems (ICECS '99), September 5-8 1999, pp. 961-964, Cyprus

• S.A. Velastin, B.A. Boghossian, A. Lazzarato (1999): “Detection of potentially dangerous situations involving crowds using image processing”, Intelligent Industrial Automation, IIA99 (special session on vision-based intelligent systems for surveillance and traffic control), June 1 – 4, 1999, Genoa, Italy.

• B.A. Boghossian, S.A. Velastin (1999): “Evaluation of motion based algorithms for automated crowd management”, Workshop on Performance Characterisation and Benchmarking of Vision Systems, International Conference on Vision Systems, ICVS, January 1999, Spain, pp. 80-96.

• Henning Schmidt, Sergio Velastin (1997), Fuzzy Control for a Robot Gripper System to Handle Slipping Objects, EUFIT97, 5th European Congress on Intelligent techniques and soft computing, Aachen, Germany, Sep. 8-11, 1997 

• Lopez M, Velastin S.A, Rodriguez M. (1997): “Towards automatic measurement of passenger density in an urban train carriage using image processing”, 8th IFAC Symp. on Transportation Systems, Crete, June 1997 

• Reinhoudt E.M, Velastin S.A (1997): A dynamic predicting algorithm for estimating bus arrival time, 8th IFAC Symp. on Transportation Systems, Crete, June 1997 

• Marana A.N., Costa L da F., Velastin S.A, Lotufo R.A. (1997): “Automatic estimation of crowd density using texture”, International Workshop on Systems and Image Processing, IWSIP’97, May 28-30, Poland

• J.P. Deparis, S.A. Velastin, A.C. Davies (1996): Telematic Tools to Help Automation in Public Transport. Example of an EC research project: Cromatica, 5th Int. Conf. on Automated People Movers (APMs), APM96, pp. 227-238, 10-14 June, Paris, France 

• J.H. Yin, S.A. Velastin, A.C. Davies (1995): “Image Processing Techniques for Crowd Estimation using a Reference Image”, Second Asian Conference on Computer Vision (ACCV95), Singapore, 5-8 December, Vol. III, pp. 6-10

• A.C. Davies, J.Y. Yin, S.A. Velastin (1995): “Crowd Monitoring using Image Processing”, IEE Electronic and Communications Engineering Journal, Vol. 7, No. 1 (February), pp. 37-47

• A.C. Davies, J.Y. Yin, S.A. Velastin (1995): “Computer-based Image Processing for the Monitoring of Crowds”, Civil Protection (UK Home Office), January.

• S.A. Velastin, J.H. Yin, M.A. Vicencio-Silva, A.C. Davies, R.E. Allsop, A. Penn (1994): "Image Processing Techniques for On-line Analysis of Crowds in Public Transport Areas", IFAC Symposium on Transportation Systems: Theory and Application of Advanced Technology (IFAC/IFORS TS'94), pp. 163-168, 24-26 August 1994, Tianjin, China