A direct part-level segmentation of range images using volumetric models

Franc Solina and Aleš Leonardis and Alenka Macerl (1994) A direct part-level segmentation of range images using volumetric models. In: IEEE Robotics and Automation, 8-13 May 1994, San Diego, CA.

Preview

PDF Download (432Kb)

Abstract

Volumetric part models play an important part in robotic applications such as grasping, path planning, object avoidance, and modeling kinematic chains. We present a novel method to reliable and efficient recovery of part-descriptions in terms of superquadric models from range images. In contrast to usual approaches which perform the recovery of volumetric models in several steps (from curves, surfaces to volumes), we show that a direct recovery is possible. This is achieved by combining two existing methods: recover-and-select paradigm and recovery of superquadric models. A redundant set of superquadrics is initiated in the image and only the recovered models resulting in the simplest overall description are selected. We show the results on several real range images.

Actions (login required)