Authors:
Frithjof Gressmann
;
Timo Lüddecke
;
Tatyana Ivanovska
;
Markus Schoeler
and
Florentin Wörgötter
Affiliation:
Georg-August-University, Germany
Keyword(s):
Object Recognition, Part Perception, Deep Learning, Neural Networks, 3D Objects.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Pattern Recognition
;
Robotics
;
Segmentation and Grouping
;
Software Engineering
Abstract:
During the last years, approaches based on convolutional neural networks (CNN) had substantial success in
visual object perception. CNNs turned out to be capable of extracting high-level features of objects, which
allow for fine-grained classification. However, some object classes exhibit tremendous variance with respect
to their instances appearance. We believe that considering object parts as an intermediate representation could
be helpful in these cases. In this work, a part-driven perception of everyday objects with a rotation estimation
is implemented using deep convolution neural networks. The used network is trained and tested on artificially
generated RGB-D data. The approach has a potential to be used for part recognition of realistic sensor
recordings in present robot systems.