ISRI > Project > Object Categorization and Self Modeling for Intelligent Manufacturing


Object Categorization and Self Modeling for Intelligent Manufacturing

Leader: Jaewoong Kim
Contact: Jaewoong Kim (

Mailing address:
Intelligent System Research Institute (ISRI)
Research Complex 2, 6th floor, Building C, Natural Sciences Campus, Sungkyunkwan University,
2066, Seobu-ro, Jangan-gu, Suwon-si,
Gyeonggi-do 440-746, South Korea
Project Description
(Top-Left) GM Motoman Robot with Structural light 3D Sensor
(Top-Right) Household Object Modeling and Kettle Modeling
(Bottom-Left) extraction geometric primitive from Alternator CAD Data, Real alternator data match CAD Model
(Bottom-Right) Alternator modeling and Pose Estimation

• Extracting the shape get the 2D and 3D image using high accuracy structure light 3D sensor..
• for household or industrial objects Approximate sphere, plane, cylinder and corn primitive geometric shape. so this method generate categorized model..
• Object without model information make primitive geometric shape combination. so object generate self modeling. this method applied to pose estimation and object recognition..
• given CAD model information for industrial robot about target object, extract primitive geometric shape. so recognition and modeling information applied that.
 NameTitleEmail Address
 Yenho leePhD
 Nguyen Huu HungPhD
 Ahmed M. NaguibMaster
Recent publications

Copyright 2007 Intelligent Systems Research Institute in Sungkyunkwan University. All right reserved. Sungkyunkwan University,

300 Cheoncheon-dong, jangan-gu, Suwon, Gyeonggi-do, 440-746, Korea

TEL : +82-31-299-6471 / FAX : +82-31-299-6479 / E-mail :