RESEARCH INTERESTS:

Intelligent video analysis, editing, and generation

Visual SLAM, 3D reconstruction for robot navigation

BEV and 3D semantic scene parsing for autonomous driving

Graphical models for image and video modeling

Deformable models and level set methods for 2D/3D image segmentation

Machine Learning for face recognition and person identification

Other related topics in computer vision, pattern recognition, robotics, and medical image analysis

RESEARCH PROJECTS:

Vision-based autonomous driving, 2022~

Monocular visual SLAM, 2020~2023

3D semantic scene parsing, 2021~2022

Intelligent video editing for surveillance and education, 2019~2022

(Editing system demo, Edited lecture demo)

Realtime interactive virtual tourism via visual localization, 2019~2021

Person search and (re)-identification for intelligent video surveillance, 2014~2020

Face liveness detection/anti-spoofing for face recognition, 2014~2015

Multi-camera multi-target tracking for business intelligence, 2014~2015

Action recognition using deep learning, 2013~2014

Object localization and categorization using graphical models, 2008~2014

Bias field estimation for medical imaging using level set methods and graphical models, 2008~2012

Sequential data analysis using generative and discriminative graphical models, 2008~2009

Shape modeling using graphical models, 2006~2009

Object segmentation using deformable models and graphical models, 2003~2008

Face recognition using subspace analysis and graphical models, 2001~2004