MaRoboticCTPointCloudAnalysis

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

Thesis: Robotic Computed Tomography: Pointcloud object extraction

Thesis by:
Advisor: Tobias Lasser
Supervision by: Erdal Pekel

Abstract

In Robotic Computed Tomography a robot places a target object in different poses between source and detector for improved reconstruction results. The motion planning pipeline for the robot relies on accurate registration of the robot's environment at system startup. In this thesis an object extraction / registration algorithm should be implemented that analyses the system state at startup and extracts objects within the operating range of the robot from the pointclouds that are received from multiple sensors.

Tasks

The aim of this thesis is the implementation of a pointcloud object extraction / registration algorithm that initialises the motion planning pipeline with the robot's surroundings at system startup.

The following tasks need to be carried out throughout the duration of the project:

  • In-depth literature review on pointcloud object extraction / registration methods
  • Implementation of different pointcloud object extraction algorithms
  • Hyper-parameter tuning
  • Performance analysis and comparison of the different approaches

Requirements

Computer Vision / Pointcloud Algorithms, C++, ROS, Interest in Robotics

Contact


Students.ProjectForm
Title: Robotic Computed Tomography: Pointcloud object extraction
Abstract: In Robotic Computed Tomography a robot places a target object in different poses between source and detector for improved reconstruction results. The motion planning pipeline for the robot relies on accurate registration of the robot's environment at system startup. In this thesis an object extraction / registration algorithm should be implemented that analyses the system state at startup and extracts objects within the operating range of the robot from the pointclouds that are received from multiple sensors.
Student:  
Director: Tobias Lasser
Supervisor: Erdal Pekel
Type: Master Thesis
Area:  
Status: open
Start: ASAP
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 20 Aug 2019 - 10:58 - ErdalPekel