Date: 21 November 2007, 14.00
Venue: EM2.33
Name: Dr S Singh, Signal Processing Lab, Cambridge University Engineering Department
The Point Processes framework is both natural and rigorous for the multiple-object tracking problem and is increasingly playing a central role in the derivation of new target tracking algorithms. Interest in this framework is largely due to the derivation of a filter that propagates the first moment of Spatial Point Processes observed in noise by Ronald Mahler. Since then there have been several extensions to this result with accompanying numerical implementations based on Sequential Monte Carlo. This talk aims to provide an overview of this new area, its applications and current research initiatives.
The point-process approach for multi-object stochastic filtering was motivated by the need to develop mathematically rigorous yet practical techniques for tracking multiple targets from sensor data. These filters have led to robust multiple-target tracking algorithms for estimating both the correct number of targets and their state vectors in data with false alarms and missed detections. These techniques have a wide range range of applications within electrical engineering and can be deployed on many different types of sensors.
Target tracking algorithms are an essential building block of systems that perform functions such as surveillance, guidance or obstacle avoidance. Tracking algorithms take their input measurements from sensors which provide the signals such as radar, sonar or video. The measurements are taken at regular intervals and the task is to estimate the state of a target at each point in time, such as its position, velocity or other attribute. Successive estimates provide the tracks which describe the trajectory of a target.
Whilst these techniques are attracting international attention within the engineering academia and in industry, they is relatively unknown within the mathematics and statistics community.
Dr Sumeetpal Singh is a Lecturer in the Engineering and Statistics departments at the University of Cambridge whose interests include developing methodologies for stochastic filtering using point processes and sequential Monte Carlo techniques.