We propose a learning system for object categorization which utilizes information from multiple sensors. The system learns not only prior to its deployment in a supervised mode but also in a self-learning mode. A competition based neural network learning algorithm is used to distinguish between representations of different categories. We illustrate the system application on an example of image categorization. A radar guides a selection of candidate images provided by the camera for subsequent analysis by our learning method. Radar information gets coupled with navigational information for improved localization of objects during self-learning. © 2009 Springer Berlin Heidelberg.
CITATION STYLE
Prokhorov, D. V. (2009). A self-learning system for object categorization. In Lecture Notes in Business Information Processing (Vol. 24 LNBIP, pp. 265–274). Springer Verlag. https://doi.org/10.1007/978-3-642-01347-8_22
Mendeley helps you to discover research relevant for your work.