DaFastContourSegmentation

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

%Fast Contour Segmentation%

Motivation

A previous thesis evaluated first methods of extracting the shilouette of persons within the view of a (mobile) camera. Based on the known camera extrinsics and the given position and shape information of the person by a people tracking system, the system segmented the person's outline such that it could be used to handle occlusions correctly. Even though the estimated results are already quite nice there is some space for further improvements regarding speed and quality. The thesis pointed out some new methods ((Fast) Level Set and GeoS?) that could be of interest for this kind of applications and that should be evaluated further.

Requirements

  • You should be motivated in AR and should have knowledge of basic image processing algorithms.
  • Knowledge of C++ is obligatory.
  • Knowledge of Matlab is auxiliary.
  • Knowledge of OpenCV is auxiliary.

Contacts:


ProjectForm
Title: Fast Contour Segmentation
Abstract: Recent advances in image processing show impressive results in deformable contour tracking and object segmentation. These novel approaches should be implemented and evaluated for the purpose of human contour tracking in real-time scenarios. The overall aim of this thesis is to evaluate and compare at least two different methods and show advantages and disadvantages of their applicabillity for AR applications.
Student:  
Director: Prof. Gudrun Klinker(Ph.D.)
Supervisor: Christian Waechter
Type: DA/MA/BA
Area: Industrial Tracking, Segmentation, Industrial Augmented Reality
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.3 - 08 Nov 2013 - 07:25 - ChristianWaechter