ISRI > Project > Line-Based Recognition

  

Line-Based Recognition

Leader: Jaekyu Lee
Contact: Jaekyu Lee (jklee1965@skku.edu)


Mailing address:
SungKyunKwan University
Intelligent System Research Center (ISRC)
Nano and Intelligent System Lab
83654 2nd Research building
300 Cheoncheon-dong, Jangan-gu,
Suwon, Gyeonggi-do
440 - 746
Korea
 
Project Description
 

In home service robot applications, a home working environment exhibits a different spectral signatures that naturally occurring phenomena. The fact that in-site environment and man made furniture objects display most straight edges bring line features to critical important features in object recognition.
We present an intelligent approach to recognize 3D objects using line structure correspondences. The approach identifies an object and estimates the pose of the object and provides the object recognition information to a home service robot system. This is done by a three-stage perceptual structure based intelligent computations as following.

1. Line structures that human usually used to describe an object is used to represent the object. A set of such representation pairs that share same properties with corresponding model line structures are first generated from images.
2. The structure correspondences are evaluated and ranked by computation of feature coverage that human used to judge recognition certainty. Only the most meaningful correspondences are selected. Each correspondence contributes a pose hypothesis consisting of a similarity transformation.
3. The approximate model pose hypotheses are estimated based on the selected correspondences.


* The framework of the Line-based Recognition

 
Personnel
 
 NameTitleEmail Address
 Jaekyu LeeResearch Professorjklee1965@skku.edu
 Zhaojin LuDoctor of Philosophyluzhaojin@gmail.com
 Quoc Hung TruongMaster Degreehungtruong@skku.edu
 
Recent publications
 
  • Dependable 3D Recognition and Modeling for Visually Guided Robotic Manipulation and Navigation
  • Sukhan Lee, Jeihun Lee, Seungmin Beak, Dongju Moon and Woong-Myung Kim
    The 5th IARP-IEEE/RAS-EURON Workshop on Technical Challenges for Dependable Robots in Human Environments (IARP07), 2007

    [Download : pdf]

  • Model Based 3D Object Recognition using Line Features
  • Samuel H. Chang, Sukhan Lee, DongJu Moon, WoongMyung Kim and YeungHak Lee
    The 13th International Conference on Advanced Robotics (ICAR 07), 2007

    [Download : pdf]

  • Recursive Particle Filter with Geometric Constraints for SLAM
  • Sukhan Lee and Seongsoo Lee
    IEEE Int. Conf. on Multisensor Fusion and Integration for Intelligent Systems (MFI2006), 2006

    [Download : pdf]



    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 : navvis@skku.edu