No 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.

No abstract

Perception of garments is a challenging task for robots due to the large variety in shapes, fabric patterns, and materials. We investigate a multi-sensorial approach, making no assumptions about the garments' configuration or properties. We use a robot equipped with RGB-D, tactile, and photometric stereo sensors that interacts with the garment through a combination of different basic actions. By applying machine learning techniques on the autonomously acquired data of different modalities we recognize the manipulated garment's type, fabric pattern, and material. Despite the challenges imposed by the unconstrained environment, promising performances are achieved for the majority of the recognition tasks.