Hide menu

Target Tracking

Course Information VT, 2019

Goal

After completing the course, the student should have the ability to describe and implement the most important concepts, methods, and algorithms used for target tracking. More specifically, after the course the student should:

  • Understand and explain the fundamental principles of target tracking and target tracking systems.
  • Know of and be able to use common target and sensor models in target tracking.
  • Know how to deal with maneuvering targets, and sensor artifacts.
  • Be able to implement a single target tracker.
  • Understand the principles behind track management and be able to implement classic multi-target tracking methods.
  • Know of modern approaches to the multi-target tracking problem.

Responsible

Prerequisites

The course assumes basic knowledge of probability theory and Bayesian estimation theory, eg, as taught in the Sensor Fusion course (TSRT14). The computer exercises will require some coding in MATLAB or similar tool. Interested students with basic knowledge of math from an engineering MSc program are expected to be able to pick up what they need on the way.

Literature:

Selected papers handed out during the course will be enough to follow the course.

For a fairly complete overview of the target tracking problem, methods, and algorithm collected at one place, the flowing books are good entry points.

  • S. Blackman and R. Popoli. Design and Analysis of Modern Tracking Systems. Archtech House, Norwood, MA. 1999.
  • Y. Bar-Shalom, P. K. Willett, and X. Tian. Tracking and Data Fusion: A Handbook of Algorithms. Yaakov Bar-Shalom Publishing. 2011.

Articles used throughout the course (this list will be updated throughout the course):

Examination

Credits for the course are awarded in three levels:

  • Short written exam covering the basic theory (2 hp)
  • Completed computer exercises (4 hp)
  • Completed project (3 hp)

Preliminary lecture plan

The times for the lectures are preliminary and up for discussion to minimize overlap with other courses.

Slides will be linked from the lecture number in advance.

Nr.WhenWhereContentSlidesMaterialExercise
1 Jan 15, 2019 10-12 Algoritmen Introduction slides, slides-4up
2 Jan 25, 2019 13-15 Algoritmen Models in target tracking slides, slides-4up [1], [2], [3], [4]
3 Feb 1, 2019 13-15 Algoritmen Single target tracking slides, slides-4up [5], [6], [7] ex 1, ex1data.mat
4 Feb 22, 2019 13-15 Algoritmen Multi-target tracking; GNN, JPDA slides, slides-4up [7], [8], [9] ex 2, ex2data.mat, auction.m, computeTrackProb.m
5 Apr 8, 2019 13-15 Algoritmen Multi-target tracking; MHT slides, slides-4up [6], [9], [10], [11], [12], [13] ex 3, murty.m
6 Apr 24, 2019 13-15 Algoritmen Random Finite Set methods; PHD, LMB. slides, slides-4up [14], [15], [16], [17], [18], [19], [20], [21], [22], [23]
7 2 May, 2019 10-12 Systemet Guest lecture: Veoneer
8 May 24, 2019 13-15 Algoritmen Various topics; TrBD, T2TF, ETT slides, slides-4up [24], [25], [26], [27], [28], [29], [30]
9 Aug 2019 Project presentation slides, slides-4up

Exercises are due Sunday the week before the next lecture (unless otherwise stated)!


Page responsible: Gustaf Hendeby
Last updated: 2019-05-24