MaEvalRegCalib

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Evaluating Applied Sensor-Registration/-Calibration

artrack.jpg

ReprojectionError.png

Description

For every Augmented Reality application a certain level of preparation is required.

The developer, for example, has to know the exact correlation between the intergrated sensors, be it RBG-,Depth- or Infrared-cameras.

Knowing this correlation means calculating the positional-/rotational-offset between each device involved.

These measurements matter a great deal for the final look-and-feel of our AR-applications. Imprecise measurements can break the entire project.

As we are looking deeper into easing this measurement-process for the user, we need to evaluate and compare the resulting registrations against each other.

Applying students will receive different measurement sets for the same sensor-registration and evaluate them.

Their evaluations will then be used to compare different approaches of sensor-registration in terms of their overall quality and precision.

For this purpose we are looking for a student with experience in either Matlab or Python.

Requirements

* Experienced in MatLab? or Python for evaluation and comparison purposes

Contact

* If you are interested write a mail with subject "Evaluating Applied Sensor-Registration/-Calibration" to application.langbein@tum.de


ProjectForm
Title: Evaluating Applied Sensor-Registration/-Calibration
Abstract: For every Augmented Reality application a certain level of preparation is required. The developer, for example, has to know the exact correlation between the intergrated sensors, be it RBG-,Depth- or Infrared-cameras. Knowing this correlation means calculating the positional-/rotational-offset between each device involved. These measurements matter a great deal for the final look-and-feel of our AR-applications. Imprecise measurements can break the entire project. As we are looking deeper into easing this measurement-process for the user, we need to evaluate and compare the resulting registrations against each other. Applying students will receive different measurement sets for the same sensor-registration and evaluate them. Their evaluations will then be used to compare different approaches of sensor-registration in terms of their overall quality and precision. For this purpose we are looking for a student with experience in either Matlab or Python.
Student:  
Director:  
Supervisor: Dr. Frieder Pankratz, Andreas Langbein, David Plecher
Type: Hiwi
Area:  
Status: open
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.6 - 18 Nov 2017 - 09:24 - AndreasLangbein