Unsupervised feature selection and category formation for mobile robot vision
Hirokazu Madokoro, Masahiro Tsukada, Kazuhito Sato · 2011
This paper presents an unsupervised learning-based method for selection of feature points and object category formation without previous setting of the number of categories. For unsupervised object category formation, this method has the following features: detection of feature points and description of features using a Scale-Invariant Feature Transform (SIFT), selection of target feature points using One Class-SVMs (OC-SVMs), generation of visual words using SOMs, formation of labels using ART-2, and creation and classification of categories on a category map of CPNs for visualizing spatial relations between categories. Classification results of static images using a Caltech-256 object category dataset and dynamic images using time-series images obtained using a robot according to movements respectively demonstrate that our method can visualize spatial relations of categories while maintaining time-series characteristics. Moreover, we emphasize the effectiveness of our method for category formation of appearance changes of objects.