Autonomous Learning of Object Appearances using Colour Contour Frames
2006 (English)In: 3rd Canadian Conference on Computer and Robot Vision, CRV06, Québec City, Québec, Canada, Québec, Canada: IEEE Computer Society , 2006, 3-3 p.Conference paper (Refereed)
In this paper we make use of the idea that a robot can autonomously discover objects and learn their appearances by poking and prodding at interesting parts of a scene. In order to make the resultant object recognition ability more robust, and discriminative, we replace earlier used colour histogram features with an invariant texture-patch method. The texture patches are extracted in a similarity invariant frame which is constructed from short colour contour segments. We demonstrate the robustness of our invariant frames with a repeatability test under general homography transformations of a planar scene. Through the repeatability test, we find that defining the frame using using ellipse segments instead of lines where this is appropriate improves repeatability. We also apply the developed features to autonomous learning of object appearances, and show how the learned objects can be recognised under out-of-plane rotation and scale changes.
Place, publisher, year, edition, pages
Québec, Canada: IEEE Computer Society , 2006. 3-3 p.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-37179DOI: 10.1109/CRV.2006.17Local ID: 33870ISBN: 0-7695-2542-3OAI: oai:DiVA.org:liu-37179DiVA: diva2:258028
3rd Canadian Conference on Computer and Robot Vision, CRV06, June 07-June. Quebec City, 3rd Canadian Conference on Computer and Robot Vision Québec, Canada