Pouria Sadeghi, PhD
- Artificial Intelligence
- Machine Learning
- Image Processing
- Objects Detection and Tracking
- Control Systems
2008-2012: Lancaster University
PhD on methods with evolving and real-time in automation video streams prepossessing and autonomous systems control. Working on image processing, objects detection and tracking, landmark recognition, robots and control systems
2007-2008: Newcastle University
MSc Automation and Control
2001-2005: Azad University
BSc Electrical Engineering
P.Sadeghi-Tehran, J.Andreu, P.Angelov, X.Zhou,Intelligent Leader-Follower Behaviour for Unmanned Ground based Vehicles, Journal of Automation, Mobile Robotics and Intelligent Systems (JAMRIS), ISSN 1897-8649, vol.5(1), pp.1-11, 2011
P.Angelov, P.Sadeghi-Tehran , R.Ramezani, A Real-time Approach to Autonomous Novelty Detection and Object Tracking in Video Stream, International Journal of Intelligent Systems, vol.26 (3) 189-205, March 2011
P.Sadeghi-Tehran, A.B.Cara, P.Angelov, H.Pomares, I.Rojas, A.Prieto, Self-Evolving Parameter-free Rule-based Controller, In Proc. 2012 World Congress on Computational Intelligence, WCCI-2012, 10-15 June 2012, Brisbane, Australia, pp.754-761 (IEEE Press, ISBN 978-1-4673-1489-3).
P.Sadeghi-Tehran , S. Behera, P.Angelov, J.Andreu, Autonomous Visual Self-Localisation in Completely Unknown Environment, In Proc. 2012 IEEE Conference on Evolving and Adaptive Intelligent Systems , EAIS-2012, 17-18 May 2012, Madrid, Spain, pp. 90-95 (IEEE Press, ISBN 978-1-4673-1727-6)
P.Sadeghi-Tehran , P.Angelov, A Real-time Approach for Novelty Detection and Trajectories Analysis for Anomaly Recognition in Video Surveillance Systems, In Proc. 2012 IEEE Conference on Evolving and Adaptive Intelligent Systems , EAIS-2012, 17-18 May 2012, Madrid, Spain, pp. 108-113 (IEEE Press, ISBN 978-1-4673-1727-6)
P.Sadeghi-Tehran, P.Angelov, Online Self-Evolving Fuzzy Controller for Autonomous Mobile Robots, IEEE Symposium Series on Computational Intelligence SSCI-2011, 11-15 April 2011, Paris, France, pp.100-107, ISBN 978-1-4244-9977-9
P.Sadeghi-Tehran, P. Angelov, R. Ramezani, A Fast Approach to Autonomous Detection, Identification, and Tracking of Multiple Objects in Video Streams under Uncertainties, In: E.Hullermeier, R.Kruse, and F.Hoffmann (Eds.): IPMU 2010, Part II, CCIS 81, pp.30-43, 2010, ISBN 3-642-14057-2 Springer Berlin Heidelberg New York, ISSN 1865-0929.
P.Angelov, C.Gude, P. Sadeghi-Tehran, T.Ivanov, ARTOT: Autonomous Real-Time Object Detection and Tracking by a Moving Camera, In Proc. 2012 IEEE Conference on Intelligent Systems , IS-12, 6-8 September, Sofia, Bulgaria
GAMMA: Growing Autonomous Mission MAnagement Systems Programme
The growing autonomous mission management applications (GAMMA) is a three year £9.1 million, autonomous systems programme aimed at driving SME engagement and developing technology within the emerging autonomous systems markets .
North West Aerospace Alliance (NWAA), BAE Systems and the Universities of Manchester, Lancaster, Salford, Central Lancashire, Liverpool (including the Virtual Engineering Centre) and the National Nuclear Laboratories are supporting the programme.
Development of methods, algorithms and software for autonomous novelty detection by moving camera
In this project a new approach and related software is developed which is completely autonomous and can work both for static and moving cameras detecting any moving objects. This will remove the direct human involvement and will reduce time and computational complexity
Intelligent Leader-Follower algorithms for ground platforms
Assisted Carriage: Intelligent Leader-follower algorithms', funded by Centre for Defence Enterprise, Ministry of Defence. An autonomous leader-follower algorithm is developed and implemented on mobile robot in an unknown and unpredictable environment.
Passive Optimal Sense and Avoid (POSA)
An Integrated Approach to Autonomous Collision Detection, and Avoidance of Uninhabited Aerial Systems, funded by BAE Systems - this project is a part of ASTRAEA, (Autonomous Systems Technology Related Airborne Evaluation & Assessment)
Lab Demonstrator: Digital Signal Processing (DSP)
Provided support for understanding the fundamentals of modern Digital Signal Processing Techniques using MATLAB and SLIFER.
Lab Demonstrator: Information and Communication Technology
Provided support for understanding the fundamentals of communication systems using Hyper Signal software.
Lab Demonstrator: Intelligent and Autonomous Systems
provided support to understand the fundamentals of the subject of artificial intelligence and autonomous systems. Also provide programming support for MATLAB and C++.
Prestigious IEEE student travel grant award, IEEE Symposium Series on Computational Intelligence
Selected out of 118 applicants to get partial funding from the prestigious (second largest in this area and largest in 2011) IEEE Symposium Series on Computational Intelligence which was held in Paris in April 2011) Also listed as the best top 3 papers in the conference
Lancaster University,School of Computing and Communications Studentship (£30,000)
Newcastle University International Postgraduate Scholarship (£4500)
School of Computing & Communications Travel Grant
An autonomous leader-follower is presented and tested in an unknown and unpredictable environment. A Fuzzy Logic Controller is used in real-time to provide a smooth following behaviour. The follower used the leader's status sent by a smart phone to differentiate between obstacles and the leader and then using two types of sensor, laser and sonar, during the obstacle avoidance procedure. In order to identify the leader again out of many obstacles around, two alternative techniques are proposed using superposition of the scans collected by the laser and predicting the leader's trajectory using evolving Takagi-Sugeno (eTS). The experiments carried out with a real-time mobile robot at Lancaster University.
A novel approach to visual self-localization in an unknown environment is presented. The proposed method makes possible the recognition of new landmark without using GPS or any other communication links or pre-training. An image-based self-localization technique is used to automatically label landmarks that are detected in real-time using a computationally efficient and recursive algorithm. Real-time experiments are carried in outdoor environment at Lancaster University using a camera mounted in car in order to build a map the local environment without using any communication links.