Simon Godsill, Jaco Vermaak, William Ng, and Jack Li, "Models and Algorithms for Manoeuvring Target Tracking using Multirate Particle Filtering", IEEE Transactions on Large Scale Dynamical Systems Workshop (accepted, subject to revision. To appear in April 2007.). ABSTRACT − Standard tracking algorithms assume identical sampling rates for the state and measurement processes. However, practical trajectories are characterised by prolonged smooth sections, with sharp, but infrequent, changes. Thus, a more parsimonious representation of the target trajectory may be obtained by adapting the state sampling rate to the nature of the data. We achieve this by assuming the state arrival times to follow a random process, typically specified as Markovian, so that state points may be allocated along the trajectory in proportion to the degree of variation. We solve the resulting variable dimension state estimation problem by developing an efficient variable rate particle filtering algorithm to recursively update the posterior distribution of the state sequence as new data becomes available. The methodology is quite general and can be applied across many models where dynamic model uncertainty occurs on-line. We demonstrate the performance of the algorithm on a challenging manoeuvring target tracking problem in clutter.

William Ng, Jack Li, Sze Kim Pang, and Simon Godsill, "Joint target detection and estimation using multirate particle filters", IEEE Transactions on Aerospace and Electronic Systems (being prepared). ABSTRACT − To be given.

William Ng, Jack Li, Sze Kim Pang, and Simon Godsill, "Multisensor-Multitarget detection and tracking using Sequential Monte Carlo Methods", IEEE Aerospace and Electronic Systems (being prepared). ABSTRACT − In this paper we present an online approach for joint detection and tracking for multiple targets with multiple sensors using sequential Monte Carlo (SMC) methods. There are three main contributions in the paper. The first contribution is the extension of the deterministic detection method proposed by the authors' previous publications to a full SMC context in which track initiation and termination are executed with sampling methods. In effect the dimensions of the particles are variable. The second is the tracking of maneouvring targets without using the multiple-model approaches. This can be achieved by recursively estimating the heading directions of the targets, followed by the sampling of the target state along these directions. In effect the use of multiple models to model target maneouvres may not be necessary. Lastly we also integrate a Markov Random Field (MRF) motion model with the framework to enable efficient and accurate tracking for interacting targets and to avoid potential track coalesce problems. With the employment of multiple sensors, central-level tracking strategy is adopted, where the observations from all active sensors are fused together for detection and tracking and a set of global tracks is maintained. Comprising the observations from distinct sensors that are close to each other, inter-sensor clusters are constructed that can increase the confidence level when new tracks are initiated and can reduce the computational load required in data association.

William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, "A hybrid method for online tracking of a variable number of targets", IEEE Aerospace and Electronic Systems (accepted, subject to revision). ABSTRACT − In this paper we present a hybrid method for online joint detection and tracking for multiple targets using Bayesian Monte Carlo methods. The proposed method is applicable to nonlinear and non-Gaussian models for the target dynamics and measurement likelihood. We first use an observation clustering algorithm to locate events or regions of interest (ROIs) within the surveillance region based on a buffer of observations. By monitoring the appearance and disappearance of the detected events, we can estimate number of targets and execute a track initiation, removal, or maintenance in a recursive fashion. No computational effort will be expended on target tracking unless these ROIs represent persistent activities. With this estimated number of targets, we then adopt a sequential Monte Carlo method for multiple target tracking with an efficient 2-D data assignment algorithm to deal with the potentially complex data association problem. Computer simulations demonstrate that the proposed approach is robust in performing joint detection and tracking for multiple targets even when the environment is hostile due to high clutter density and low target detection probability. In addition, in the case where the targets make weak maneuvers the proposed method can perform joint target detection and estimation in the absence of multiple model approach.

William Ng, J.P. Reilly, T. Kirubarajan, and J.R. Larocque, "Wideband Signal Processing Using MCMC Methods", IEEE Transactions on Signal Processing, Vol. 50, No. 2, Feb. 2005, pg. 411 - 426. ABSTRACT − This paper proposes a novel wideband structure for array signal processing. A new interpolation model is formed where the observations are linear functions of the source amplitudes but nonlinear in the direction of arrival (DOA) parameters. The interpolation model also applies to the narrowband case. The proposed method lends itself well to a Bayesian approach for jointly estimating the model order and the DOAs through a reversible jump Markov chain Monte Carlo procedure. The source amplitudes are estimated through a maximum a posteriori (MAP) process. Advantages of the proposed method include joint detection of model order and estimation of the DOA parameters, the fact that reliable performance can be obtained using significantly fewer observations than previous wideband methods, and that only real arithmetic is required. The DOA estimation performance of the proposed method is compared with the theoretical Cramér–Rao lower bound for this problem. Simulation results demonstrate the effectiveness and robustness of the method.

J.R. Larocque, William Ng, and J.P. Reilly, "Particle Filters for Tracking an Unknown Number of Sources", IEEE Transactions on Signal Processing, Vol. 50, No. 12, December 2002, pg. 2926-2937. ABSTRACT − This paper addresses the application of sequential importance sampling (SIS) schemes to tracking directions of arrival (DOAs) of an unknown number of sources, using a passive array of sensors. This proposed technique has significant advantages in this application, including the ability to detect a changing number of signals at arbitrary times throughout the observation period and that the requirement for quasistationarity over a limited interval may be relaxed. We propose the use of a reversible jump Monte Carlo Markov chain (RJMCMC) step to enhance the statistical diversity of the particles. This step also enables us to introduce two novel moves that significantly enhance the performance of the algorithm when the DOA tracks cross. The superior performance of the method is demonstrated by examples of application of the particle filter to sequential tracking of the DOAs of an unknown and nonstationary number of sources and to a scenario where the targets cross. Our results are compared with the PASTd method.

1. Jack Li, William Ng, and Simon Godsill, "Online multiple target tracking and sensor registration using Sequential Monte Carlo Methods", accepted by IEEE Aerospace Conferences 2007.
2. William Ng, Jack Li, and Simon Godsill, "Online Multisensor-Multitarget Detection and Tracking Using Variable Rate Particle Filters", accepted by IEEE Aerospace Conferences 2007.
3. William Ng, Sze Kim Pang, Jack Li, and Simon Godsill, "On tracking applications using variable rate particle filters", the proceedings of the IEEE Nonlinear Statistical Signal Processing Workshop (NSSPW): Classical, Unscented and Particle Filtering Methods 2006.
4. Jack Li, William Ng, and Simon Godsill, "Online target tracking and sensor registration using Sequential Monte Carlo Methods", the proceedings of the IEEE Nonlinear Statistical Signal Processing Workshop (NSSPW): Classical, Unscented and Particle Filtering Methods 2006.
5. William Ng, Sze Kim Pang, Jack Li, and Simon Godsill, "Efficient variable rate particle filters for tracking manoeuvring targets using an MRF-based motion model", the proceedings of the European Signal Processing Conference 2006.
6. William Ng, Jack Li, and Simon Godsill, " Multiple and extended object tracking with Poisson spatial process and variable rate filters", the proceedings of the First IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2005.
7. William Ng, Jack Li, and Simon Godsill, " Online multisensor-multitarget detection and tracking", the proceedings of the IEEE Aerospace Conferences 2006.

1. William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, "Tracking variable number of targets using Sequential Monte Carlo Methods", proceedings of the IEEE Statistical Signal Processing 2005.
2. William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, "A review of recent results in multiple target tracking", the proceedings of the International Symposium on Image and Signal Processing and Analysis 2005.
3. Jack Li, William Ng, Simon Godsill, and Jaco Vermaak, "Online Multitarget Detection and Tracking Using Sequential Monte Carlo Methods", the proceedings of the Eighth International Conference on Information Fusion 2005.
4. William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, "Tracking variable number of targets using Sequential Monte Carlo Method", the proceedings of the European Signal Processing Conference 2005.
5. William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, " A hybrid approach for online joint detection and tracking for multiple targets", IEEE Aerospace Conferences 2005.
6. William Ng, Jack Li, Simon Godsill, and Jaco Vermaak, "Multiple target tracking using a new soft-gating approach and sequential Monte Carlo methods", International Conference on Acoustics, Speech, and Signal Processing 2005.

1. William Ng, J.P. Reilly, and T. Kirubarajan, "A Bayesian Approach to Tracking Wideband Targets Using Sensor Arrays and Particle Filters", Proceedings of the Statistical Signal Processing, 2003, St. Louis, Missouri, paper no. 69.
2. William Ng, J.P. Reilly, and T. Kirubarajan, "Application of Particle Filters for Tracking Moving Receivers in Wireless Communication Systems", Proceedings of the Signal Processing Advances In Wireless Communications, 2003, Rome, Italy, paper no. 316.
3. William Ng, J.P. Reilly, and T. Kirubarajan, "Wideband Signal Processing Using MCMC Methods", Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, 2003, Hong Kong, Vol. 5, pg. 189-192.
4. William Ng, J.P. Reilly, T. Kirubarajan, and J.R. Larocque, "Wideband Signal Processing Using MCMC Methods", Proceedings of the IEEE Sensor Array and Multichannel, 2002, Washington, D.C., pg. 350-354.
5. William Ng, J.R. Larocque, J.P. Reilly, "Sequential MCMC for Spatial Signal Separation and Restoration From An Array of Sensors", Bayesian Inference and Maximum Entropy Methods in Science and Engineering, American Institute of Physics Conference Proceedings, Baltimore, Maryland, 2001, pg. 89-108.
6. William Ng, J.R. Larocque, J.P. Reilly, "On The Implementation of Particle Filters For DOA Tracking", Proceedings of the International Conference on Acoustics, Speech, and Signal Processing 2001, Salt Lake City, Utah, Vol. 5, pg. 2821 - 2824.

1. William Ng, "Advances in Wideband Array Signal Processing Using Numerical Bayesian Methods," McMaster University, 2004.

1. William Ng, J.R. Larocque, J.P. Reilly, "Sequential MCMC for Spatial Signal Separation and Restoration From An Array of Sensors," Bayesian Inference and Maximum Entropy Methods in Science and Engineering, American Institute of Physics Conference Proceedings, AIP, 2002.