ISRI > Project

Projects in the Intelligent Systems Research Institute
List of the previous and on going projects.
This project aims to use Autoexpose algorithms and technologies developed inside ISRC labs, cameras, and collaborate with companies to precisely process materials.
Mental Health Monitoring
This project collects and analyzes digital phenotype and SNS data to develop a standard predictive/analytical deep learning model and monitoring platform for the mental health (depression, anxiety, and suicide risk) of college students
Edge Brain
This Team is working on the vision solution to cooperate the whole process. we are doing 6D pose estimation and detection, segmentation. Also we doing research of data augmentation for life long incremtental learning.
3D Recognition
To Recognize the 3D Object, 3D Object Position and Rotation In Real-time
Integrating indoor autonomous navigation system technology and intelligent Vision recognition
Using Liver Ultrasound image and Deep Learning ,find the probe Location, Tracking using IMU sensor and cooperate with Liver Feature Extraction
Transfer human Vision Ability to human Hearing Ability using Deep Learning
Using Reinforcement Learning, The robot deliver the parcel
Estimate the Vital Sign using Hyper Spectral Camera
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.
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.
Lunar Rover
Creating a 3-D Map of the Surrounding Area and Recognizing Obstacles for Korean-type Lunar Exploration Rovers
Autonomous Driving for A Transformable Robot for Personal Care
Visual Attention/Interaction
Space Robotics
Developing a high precision vision based 6D SLAM technologies for long range rover localization
ElectroHydroDynamic Inkjet Printing System and MEMS Fabrication
Medical Robotics
Object Categorization and Self Modeling for Intelligent Manufacturing
Gyeonggi Province International Collaborative Research
21c Frontier
Converging Research Center Program
Our research focuses on a novel augmented cognition model based on the information processing mechanism of human brain.
World Class University(WCU)
Our research focuses on the goal-driven perceptual attention and the cognitive robotic engine (CRE) for natural human robot interaction.
Cognitive Consumer Robotics (HomeMate)
In this project, we will develop original key technologies that enable consumer robots to perform human-like, naturally self-contained yet highly dependable, robotic services, such as elderly-care, home security, and errand services.
Auto Exposure
In structured light system, the projector illuminates patterns, and the patterns captured by the camera are decoded.
3D Camera HW based on Structured Light
We have two types of 3D Camera HW. First, 3D IR Camera based on structured light suitable for robots working in home environment. Because IR light is employed in order to achieve human friendliness and robustness in illumination variation.
3D reconstruction
To encode a position, we assign a unique address in each position of the projector's image.
Robot Behavioral Personality
We have been developing a robot personality system to make the robot having various characters.
Caller Identification
This project team has been developing the system for accomplishing of the caller identification mission based on cognitive robotic engine.
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.
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.
3D Workspace Modeling
To provide a robot with a 3D Workspace model for manipulation planning a human-like real-time workspace modeling is proposed where modeling is done by integrating the 3D object/environment.
Self Modeling
Self Modeling for Home Service Robot.
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.

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 :