TY  - GEN
TI  - Contour Methods for View Point Tracking
Y1  - 2009///
KW  - view point tracking 
KW  -  shape manifolds 
KW  -  2D outline shape 
KW  -  level sets
ID  - heidok9684
N2  - Shape of objects, in particular the shape of object outlines, has for a long time been a focus in the literature and is widely regarded as carrying important information for visual and cognitive tasks, such as object recognition and object tracking. This thesis is concerned with techniques related to shape information from 2D images. The main contribution is a purely 2D shape based method for following view point changes of an observer relative to an object given an image sequence. Several techniques involved in such a task are covered in some detail. In particular, segmentation methods yielding contours, and shape representations are treated. On the shape side, classical representations and methods are included to a smaller extent, and a more recent, more sophisticated manifold of shapes including computational technicalities is  treated in more detail. Variational segmentation methods based on the successful level set representation are used for segmenting and tracking curves in image sequences. While this field has grown rapidly and is still developing further, this work covers enough detail to describe the implementation used for experiments, as well as useful extensions to the basic methods. Finally, a method for tracking a view point relative to a moving object based only on 2D shape information is  investigated and applied in experiments with some success. Future directions as well as limits of a purely outline based method are examined. 
UR  - https://archiv.ub.uni-heidelberg.de/volltextserver/9684/
AV  - public
A1  - Gosch, Christian
ER  -