Research Projects
· 2023-11 ~ 2024-10 3D Space Reconstruction and Visualization for Spatial AI (MobilTech)
· 2023-06 ~ 2024-05 Development of AI-based HD Map Building for Smart Farm Agricultural Robots (Ministry of Science and ICT)
· 2023-03 ~ 2025-02 Simultaneous Localization and Mapping using Multimodal Sensor Fusion (Kwangwoon University)
· 2022-11 ~ 2023-10 3D HD Map Generation for Autonomous Driving (MobilTech)
· 2021-11 ~ 2022-10 SLAM Algorithm Improvement for Autonomous Driving (MobilTech)
· 2020-03 ~ 2023-02 Multisensor Mobile Mapping System for Creating, Updating and Analyzing Digital Twins (NRF Korea)
Dynamic Object Detection for Autonomous Driving
Objectives: Detecting arbitrary moving objects in the scene
Needs: Improving safety in case that deep learning-based object detection fails or moving objects are not in traing datasets
Method: 3D Computer Vision (Epipolar Geometry)
Issues: Hard to tell if the objects seems to move because the vehicle is moving or they are moving by themselves
Multi-modal Sensor Fusion for SLAM
Objectives: Combining different sensors to make SLAM more robust to challenging environments such as wide-open areas and corridors
Sensors
LiDAR: Geometric information
Camera: Texture information
IMU Sensor: Ego-centric motion
GPS Sensor: Absolute position
Method: Continuous-time trajectory to combine asynchronous sensor data
Real-time Visual Odometry using an RGB-D Camera
Objectives: Tracking the camera pose in real-time using an RGB-D camera to overlay virtual objects on augmented reality glasses
Method: Using the depth uncertainty as weights of the depth residuals in optimization based on the sensor model of the RGB-D camera
Results: Real-time camera pose tracking more robust to intensity change and depth noise