DocumentCode :
3525876
Title :
Multi-scale superquadric fitting for efficient shape and pose recovery of unknown objects
Author :
Duncan, Kate ; Sarkar, Santonu ; Alqasemi, Redwan ; Dubey, Richa
Author_Institution :
Comput. Sci. & Eng. Dept., Univ. of South Florida, Tampa, FL, USA
fYear :
2013
fDate :
6-10 May 2013
Firstpage :
4238
Lastpage :
4243
Abstract :
Rapidly acquiring the shape and pose information of unknown objects is an essential characteristic of modern robotic systems in order to perform efficient manipulation tasks. In this work, we present a framework for 3D geometric shape recovery and pose estimation from unorganized point cloud data. We propose a low latency multi-scale voxelization strategy that rapidly fits superquadrics to single view 3D point clouds. As a result, we are able to quickly and accurately estimate the shape and pose parameters of relevant objects in a scene. We evaluate our approach on two datasets of common household objects collected using Microsoft´s Kinect sensor. We also compare our work to the state of the art and achieve comparable results in less computational time. Our experimental results demonstrate the efficacy of our approach.
Keywords :
curve fitting; geometry; image sensors; object detection; pose estimation; robot vision; shape recognition; 3D geometric pose estimation framework; 3D geometric shape recovery framework; 3D point clouds; Microsoft Kinect sensor; computational time; household object datasets; low latency multiscale voxelization strategy; manipulation tasks; multiscale superquadric fitting; object pose parameter estimation; object shape parameter estimation; robotic systems; unknown object pose information acquisition; unknown object pose recovery; unknown object shape information acquisition; unknown object shape recovery; unorganized point cloud data; Fitting; Robot sensing systems; Standards;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2013 IEEE International Conference on
Conference_Location :
Karlsruhe
ISSN :
1050-4729
Print_ISBN :
978-1-4673-5641-1
Type :
conf
DOI :
10.1109/ICRA.2013.6631176
Filename :
6631176
Link To Document :
بازگشت