ISRI > Team > 3D Recognition


3D Recognition

Team Leader: Seung Lee
Contact: Seung Lee (

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
Team Description

To realize service robots with the capability of visually guided human-like manipulation in an unstructured environment cluttered with various daily life objects, it is crucial to guarantee dependability in visual perception. In order to solve such critical issues as robustness and real-time processing in vision based 3D recognition and pose estimation, we are developing a novel vision based framework designed under the concept of “behavioral perception."

The main features of our approach as follows:

- Behavioral Perception: Dependability of perception may not come from the perfection of individual components, but from the integration of individual components into dependable system behaviors that guarantees reaching perceptual goals.
- Automatic selection and collection of an optimal set of evidences based on in-situ monitoring.
- A probabilistic and spatial-temporal integration of top-down and bottom-up perceptual processes: multiple evidence-model matching in a sequence of images based on particle filtering till reaching a credible decision.

* Overall Framework

Currently, we are focusing on developing 3D recognition system using FER-CNN and an image translation approach based on deep learning.

 Ahmed M. NaguibPhD
 Naeem Ul IslamPhD,
 Yang YongJunMaster
 Jaeeun SongMaster
 Lee SoojinPhD
 Jonghwan ShinMaster
Current Projects
Line-Based Recognition
This project group members have been developing a recognition system based on 3D line features for identifying of an object and estimating of the pose of it.
Automatic Evidence Selection and Collection
We are developing novel automatic evidence selection & collection method based on Bayesian theorem for object recognition and pose estimation in real environment.
Particle Filtering Framework
we are developing a particle filter based probabilistic method for recognizing an object and estimating its pose based on a sequence of images.
21c Frontier
FER-CNN has capability of not only extracting but also reconstructing a hierarchy of features with the layer-wise independent feedback connections that can be trained.
Image Translation
The features reconstructed by the feedback CNN represent those learned by the feedforward CNN. By analyzing how clusters are formed in the layers of feature spaces in the feedback CNN, we can interpret which features critically contribute to recognition.
3D Recognition
To Recognize the 3D Object, 3D Object Position and Rotation In Real-time
Recent publications
  • Particle Filter Based Robust Recognition and Pose Estimation of 3D Objects in a sequence of images
  • Sukhan Lee, Jeihun Lee, Seungmin Beak and Changhyun Choi
    Lecture Notes In Control and Information Sciences, 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]

  • 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]

  • Robust Recognition and Pose Estimation of 3D Objects Based on Evidence Fusion in a Sequence of Images
  • Sukhan Lee, Seongsoo Lee, Jeihun Lee, Dongju Moon and Kim Eunyoung
    IEEE International Conference on Robotics and Automation (ICRA), 2007

    [Download : pdf]

  • Recursive Unscented Kalman Filtering based SLAM using a Large Number of Noisy Observations
  • Sukhan Lee, Seongsoo Lee and Dongsung Kim
    International Journal of Control, Automation, and Systems, 2006

    [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 :