About Optional Projects
- For people who would like to do more and get more points (3hp), there is an opportunity to do a project (optional) which can take place after the course is finished.
- The aim of the projects is to gain additional knowledge on the tracking theory and algorithms.
- Depending on the amount of work required, you can work in groups, at most, of 2 people.
Possible Project SubjectsWe are going to implement most of the conventional algorithms with standard sensor models in the course. So possible project ideas are the study and implementation of
- Some conventional algorithm with unconventional sensors or
targets (important probabilistic modeling work on the sensor
and the target is required) e.g.,
- extended targets
- unresolved targets
- Some unconventional algorithm e.g.,
- track before detect
- random set based approaches (e.g., PHD, CPHD, MeMBer filters)
- (joint) integrated PDA
- probabilistic MHT
- symmetric measurements
ProcedureThe groups must communicate with the instructor at each step and reach a consensus on what to do and submit. This should start even before the project proposal. The deliverables to be submitted are
- Project proposal (a <2 page document): This should be given during the course with a tentative time schedule of what is going to be done when. Instructor's feedback and comments for the project content need to be taken into consideration in the following phases.
- Progress report (halfway during the project): This is to list the things done during the first half of your project schedule. What has been learned, read, implemented, some preliminary results, derivations of models, algorithms if any etc.
- Final report
Comments and an Example
- Of course, there is no novelty expectation from the project.
- To repeat once more, the aim is to make the student learn more about target tracking algorithms and theory and to make him/her add one more tool to his/her background.
- In the last period the course was given, there was only one group who did a project which resulted in this publication whose significantly improved version was later submitted to a journal as a correspondence.
- One must still note that this is an exceptional case and the minimum expectation from the project is only limited to getting a reasonable knowledge of the models and methods implemented.
Informationsansvarig: Torkel Glad
Senast uppdaterad: 2013-04-03