Department of Computer Science Technische Universitaet Muenchen
Home People Teaching Research Publications Info Sitemap
IAS | Image Understanding | Med | MQM

Publications

Sorted by DateClassified by Publication TypeClassified by Research CategoryClassified by Research GroupClassified by Author Last Name

Matthias Wimmer, Christoph Mayer, Freek Stulp, and Bernd Radig. Estimating Natural Activity by Fitting 3D Models via Learned Objective Functions. In Workshop on Vision, Modeling, and Visualization (VMV), pp. 233–241, Saarbrücken, Germany, November 2007.

Download

[PDF]15.1MB  

Abstract

Model-based image interpretation has proven to robustly extract high-level scene descriptors from raw image data. Furthermore, geometric texture models represent a fundamental component for visualizing real-world scenarios. However, the motion of the model and the real-world object must be similar in order to portray natural activity. Again, this information can be determined by inspecting images via model-based image interpretation. This paper sketches the challenge of fitting models to images, describes the shortcomings of current approaches and proposes a technique based on machine learning techniques. We identify the objective function as a crucial component for fitting models to images. Furthermore, we state preferable properties of these functions and we propose to learn such a function from manually annotated example images.

BibTeX Entry

@inproceedings{ wimmer07estimating,
  author    		= {Matthias Wimmer and Christoph Mayer and Freek Stulp and Bernd Radig},
  title     		= {Estimating Natural Activity by Fitting {3D}~Models via Learned Objective Functions},
  booktitle 		= {Workshop on Vision, Modeling, and Visualization~(VMV)},
  year      		= {2007},
  month				= {November},
  address   		= {Saarbr\"ucken, Germany},
  volume = {1},
  pages			= {233-241},
  bib2html_pubtype	= {Refereed Workshop Paper},
  bib2html_rescat   = {Image Understanding},
  bib2html_groups   = {IU},
  abstract          =
                        {Model-based image interpretation has proven to robustly extract high-level
                        scene descriptors from raw image data. Furthermore, geometric texture models
                        represent a fundamental component for visualizing real-world scenarios.
                        However, the motion of the model and the real-world object must be similar
                        in order to portray natural activity. Again, this information can be    determined by inspecting images via model-based image interpretation.
                        This paper sketches the challenge of fitting models to images, describes the shortcomings of current approaches and proposes a technique based on machine learning techniques. We identify the objective function as a crucial component for fitting models to images. Furthermore, we state preferable properties of these functions and we propose to learn such a function from manually annotated example images.},
}

Generated by bib2html.pl (written by Patrick Riley ) on Wed Jul 23, 2008 15:47:52 UTC


Computer Science IX | Technische Universität München