Register now After registration you will be able to apply for this opportunity online.
Fiducial Marker Enhancement for High-Accuracy AR Applications
Augmented Reality (AR) devices find their into a variety of enterprise use cases with increasing frequency and are often used to simplify and improve existing workflows. A majority of these use cases attach virtual content to real world environments, to static or even moving objects, but others require highly accurate relative poses between two or more markers to benefit the user.
AR applications already use fiducial markers (i.e April Tags) for such scenarios for many years. Markers are detected and identified in a camera image using a detector and then based on its geometry and features the marker's 3D pose is estimated. To achieve higher accuracy, algorithms can apply several refinement methods to minimize the pose error.
However high-accuracy applications often require more reliability, precision and update frequency than conventional markers can provide and the deployment of external navigation systems that fulfill these requirements is often very costly and come with their own downsides and limitations.
Keywords: AR, 3D Geometry
In order to close this gap you will study promising approaches from research and apply these and your own ideas to meet the challenging requirements of high-accuracy use cases from medical procedures and manufacturing processes.
In order to close this gap you will study promising approaches from research and apply these and your own ideas to meet the challenging requirements of high-accuracy use cases from medical procedures and manufacturing processes.
You will enhance existing marker designs or design your own, collect data using the Magic Leap 2 sensor suite, evaluate your pose estimation and refinement implementations with the help of high-accuracy ground truth methods and compare them with existing research.
You are:
A motivated Master's student with an excellent background in Computer Vision, 3D geometry and mathematical optimization. Additional knowledge in machine learning techniques for Computer Vision is beneficial, but not required. Knowledge of C++ is mandatory, knowledge of Python is a plus.
You will enhance existing marker designs or design your own, collect data using the Magic Leap 2 sensor suite, evaluate your pose estimation and refinement implementations with the help of high-accuracy ground truth methods and compare them with existing research.
You are:
A motivated Master's student with an excellent background in Computer Vision, 3D geometry and mathematical optimization. Additional knowledge in machine learning techniques for Computer Vision is beneficial, but not required. Knowledge of C++ is mandatory, knowledge of Python is a plus.
Master Project Marker Tracking.docx.pdf
