Pose and category recognition of highly deformable objects using deep learning
Authors:
- 1 July 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 655-662
Abstract
Category and pose recognition of highly deformable objects is considered a challenging problem in computer vision and robotics. In this study, we investigate recognition and pose estimation of garments hanging from a single point, using a hierarchy of deep convolutional neural networks. The adopted framework contains two layers. The deep convolutional network of the first layer is used for classifying the garment to one of the predefined categories, whereas in the second layer a category specific deep convolutional network performs pose estimation. The method has been evaluated using both synthetic and real datasets of depth images and an actual robotic platform. Experiments demonstrate that the task at hand may be performed with sufficient accuracy, to allow application in several practical scenarios.Keywords
This publication has 21 references indexed in Scilit:
- Autonomous active recognition and unfolding of clothes using random decision forests and probabilistic planning2014
- A new approach to clothing classification using mid-level layers2013
- A geometric approach to robotic laundry foldingThe International Journal of Robotics Research, 2011
- Perception for the manipulation of socks2011
- Classification of clothing using interactive perception2011
- Bringing clothing into desired configurations with limited perception2011
- A 2D Human Body Model Dressed in Eigen Clothing2010
- Composite Templates for Cloth Modeling and Sketching2006
- Learning methods for generic object recognition with invariance to pose and lighting2004
- Planning strategy for task of unfolding clothesRobotics and Autonomous Systems, 2000