DocumentCode :
3129148
Title :
3D pose estimation for bin-picking task using convex hull
Author :
Xu, Jie ; Pu, Songtao ; Zeng, Gang ; Zha, Hongbin
Author_Institution :
Machine Perception Lab., Peking Univ., Beijing, China
fYear :
2012
fDate :
5-8 Aug. 2012
Firstpage :
1381
Lastpage :
1385
Abstract :
Object pose estimation in bin-picking task is an important problem in the industry. Since objects shapes are very different, there not exists a general method now to deal with all kinds of objects. Here we use convex hulls of the planes of the objects to do object 3D pose estimation. This method ignores details of objects shapes, and is robust in matching. Our method is applicable for all the objects with planes. The experiments show that our method is efficiency and fast, and is applicable in real-time bin-picking task.
Keywords :
bin packing; image matching; pose estimation; solid modelling; 3D pose estimation; convex hull; object matching; object pose estimation; real-time bin-picking task; Computational modeling; Design automation; Estimation; Feature extraction; Shape; Solid modeling; Vectors; Bin-picking; Convex hull; Pose estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mechatronics and Automation (ICMA), 2012 International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4673-1275-2
Type :
conf
DOI :
10.1109/ICMA.2012.6284338
Filename :
6284338
Link To Document :
بازگشت