Universität Bielefeld Electronic Collections animiertes Foto Universität Bielefeld

Access to the Document



SVM-based Transfer of Visual Knowledge Across Robotic Platforms

Luo, Jie ; Pronobis, Andrzej ; Caputo, Barbara

The 5th International Conference on Computer Vision Systems, 2007
Bielefeld, 21. - 24. März 2007

Download file

Abstract:
This paper presents an SVM--based algorithm for the transfer of knowledge across robot platforms aiming to perform the same task. Our method exploits efficiently the transferred knowledge while updating incrementally the internal representation as new information is available. The algorithm is adaptive and tends to privilege new data when building the SV solution. This prevents the old knowledge to nest into the model and eventually become a possible source of misleading information. We tested our approach in the domain of vision-based place recognition. Extensive experiments show that using transferred knowledge clearly pays off in terms of performance and stability of the solution.


Keywords: continuous learning, place recognition, support vector machines
Institution: Faculty of Technology, Research Groups in Informatics
DDC classification: Data processing, computer science, computer systems

Suggested Citation:
Luo, Jie ; Pronobis, Andrzej ; Caputo, Barbara  (2007)  SVM-based Transfer of Visual Knowledge Across Robotic Platforms. The 5th International Conference on Computer Vision Systems, 2007


URL: http://biecoll.ub.uni-bielefeld.de/volltexte/2007/27



 Questions or comments: publikationsdienste.ub@uni-bielefeld.de
 Latest update: 15 Feb 2011
 Legal Notice
OPUS-Logo     OAI compliant      BU Logo
OAI-Logo