Hide menu

Dynamic Vision, Graduate Course

Projects

During the course you are encouraged to carry out a project (1-4 students in each team), although it is not mandatory. The main purpose of these projects is to provide the opportunity to learn more about a concepts relevant to the course and for successfully doing this you will have a lot of fun and get payed 3hp. Some of the projects will probably produce fruitful ideas for new research directions.


Timetable

Date Action
February 11 Project proposal are due
February 13 (9-11) Project proposal presentation
(in Systemet)
March 18 Progress reports are due
May 5 Final reports are due
May 7 Final project presentation

Brief description of the steps mentioned above.
  • Project Proposal: The report should explain the project background, the idea and how the work will be carried out. Upper page limit: 2. For the presentation, each team has 10 min. for presentation and 5 min. for discussion.
  • Progress Report: This report describes the current status of the project, what has been achieved are what are the problems to overcome. Upper page limit: 5.
  • Final Report: Final project report, clearly explains what has been accomplished within the project.
  • Final Presentation: We will use the presentation form used at most conferences, that is each team has 15 min. for presentation and 5 min. for discussion. These time limits are strict.

Active Projects

Project Team
Dynamic vision and Manifold
Learning for Control		 Henrik Ohlsson
Automotive Visual Odometry
During Extreme Manoeuvres		 Christian Lundquist
Environmental Segmentation
using Dimension Reduction
Jonas Callmer
Fredrik Lindsten
Henrik Ohlsson
Camera IMU SLAM using an Optimization Approach Zoran Sjanic
Martin Skoglund
Boosting Karl Granström
Visual Odometry and Estimation of 3D Orientation for Autonomous Vehicles Peter Nordin
Per Skoglar


Projects Ideas

Here is a very brief list of idea on projects that could be performed within the course. Own ideas are most appreciated! Since the course is linked to (and partly co-lectured) the course in robotics, joint projects are highly recommended.

  • Robotic - vision projects
  • Autonomous UAV landing in unknown environments: The task is to design and implement an estimator for autonomous UAV landing, when there is no landing pad available. This implies that the estimator must, besides the UAV state, deliver a map of the terrain under the UAV.
  • Vehicle tracking: Detecting and tracking leading vehicles in camera images recorded from a camera attached in the front window of a moving vehicle.
  • Fido SLAM: Using our ground robot Fido attached with a camera to build maps and localize the Fido within this map. In other words solving the simultaneous localization and mapping (SLAM) problem.
  • Youtube is a good place for inspiration.

A few more detailed project ideas are available here.


Page responsible: Thomas Schön
Last updated: 2024-08-20