Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching
2007 (English)In: Proceedings 15th Scandinavian Conference on Image Analysis / [ed] Bjarne K. Ersboll and Kim S. Pedersen, Berlin, Heidelberg: Springer-Verlag , 2007, Vol. 4522, 908-917 p.Conference paper (Refereed)
In this paper we propose a new approach to real-time view-based object recognition and scene registration. Object recognition is an important sub-task in many applications, as e.g., robotics, retrieval, and surveillance. Scene registration is particularly useful for identifying camera views in databases or video sequences. All of these applications require a fast recognition process and the possibility to extend the database with new material, i.e., to update the recognition system online. The method that we propose is based on P-channels, a special kind of information representation which combines advantages of histograms and local linear models. Our approach is motivated by its similarity to information representation in biological systems but its main advantage is its robustness against common distortions as clutter and occlusion. The recognition algorithm extracts a number of basic, intensity invariant image features, encodes them into P-channels, and compares the query P-channels to a set of prototype P-channels in a database. The algorithm is applied in a cross-validation experiment on the COIL database, resulting in nearly ideal ROC curves. Furthermore, results from scene registration with a fish-eye camera are presented.
Place, publisher, year, edition, pages
Berlin, Heidelberg: Springer-Verlag , 2007. Vol. 4522, 908-917 p.
, Lecture Notes in Computer Science, ISSN 1611-33490 ; Volume 4522
Object recognition - scene registration - P-channels - real-time processing - view-based computer vision
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-21618DOI: 10.1007/978-3-540-73040-8ISBN: 978-3-540-73039-2OAI: oai:DiVA.org:liu-21618DiVA: diva2:241583
15th Scandinavian Conference, SCIA 2007, June 10-24, Aalborg, Denmark
Michael Felsberg and Johan Hedborg, Real-Time Visual Recognition of Objects and Scenes Using P-Channel Matching, 2007, Proc. 15th Scandinavian Conference on Image Analysis, 908-917.