Kalman Filtering and Tracking
Subject code: SIP 7002
Lecturer
Prof. Iven Mareels
The University of Melbourne
Mode of delivery
On-line with a possibility of a short course.
Assumed knowledge
Linear algebra (matrices), probability theory, linear systems and MATLAB.
Aim/Learning Objectives
This course focuses on the Kalman filter design and applications. Topics
include the basic knowledge of Kalman filtering, Kalman filter design and
implementations as well as the applications. The course consists of a series of
lectures and tutorials aimed at helping students understand the idea and
implementations of the Kalman filter and related topics.
At the completion of the course students will have knowledge of the theory and
applications of the Kalman filter in the area of signal processing (and
control). The course outcomes are to provide both theoretical and practical
skills necessary to design and implement Kalman filter algorithms.
Content
The Kalman Filter:
Stochastic state-variable systems,
Optimality criteria for the estimation of state variables;
The Maximum-likelihood solution for independent Gaussian noise processes;
The innovations sequence;
The least-squares Kalman filter; Systems with correlated noise processes;
Stochastic systems with time-invariant coefficients;
The square-root algorithm;
The extended Kalman filter, Adaptive system identification.
Tracking Theory:
Alpha-beta trackers, Kalman-filter tracking;
Probability Data Association Tracking Hidden Markov models and the
Viterbi Algorithm.
Assessment
Details of the actual assessment used in a given year
can be found in the study guide provided at the start of the semester.
Resources
All the materials necessary for the course will be availabe on-line. The
lecture notes are based on the following text books:
- A. V. Balakrishnan, (1984) Kalman Filtering Theory.
Optimization Software, Inc.
- Mohinder S. Grewal and Angus P. Andrews, (2001) Kalman Filtering:
Theory and Practice using Matlab. Second edition, John Wiley & Sons, Inc.