Skip to content
@VIPLAB-Gachon

Vehicle Intelligence & Perception Lab @ Gachon University

Vehicle Intelligence & Perception Lab @ Gachon University

VIP-LAB

Vehicle Intelligence & Perception Laboratory

Gachon University, Republic of Korea

Ground-to-Air Robust Robot Vision 지상에서 상공까지, 어떤 환경에서도 무너지지 않는 로봇 비전

Homepage YouTube Google Scholar Email


👋 About Us

We develop perception systems that keep working where conventional autonomous driving fails — on unpaved terrain, in rain and snow, and hundreds of meters above the ground. Our work spans LiDAR, camera, radar, and thermal (EO/IR) sensing, from algorithm design to real-time deployment on embedded hardware.

가천대학교 차량지능·인지 연구실(VIP-LAB)은 비포장 야지, 악천후, 항공 플랫폼처럼 기존 자율주행이 한계를 보이는 환경에서 동작하는 인지 시스템을 연구합니다. 라이다·카메라·레이더· 열화상을 아우르는 다중 센서 인지부터 임베디드 실시간 배포까지 다룹니다.

PI: Prof. Jhonghyun An (안종현) · Associate Professor, Dept. of AI-Software


🔬 Research Directions

Direction Keywords
🏔️ Off-Road & Adverse-Weather Perception traversability, all-weather LiDAR segmentation, domain generalization
🛩️ EO/IR & Aerial Perception thermal detection, RGB–thermal adaptation, small-object detection
Efficient On-Device AI knowledge distillation, pruning, NAS, quantization
🤖 Multi-Robot Mapping & Physical AI wide-area semantic maps, change detection, end-to-end driving

📦 Repositories

📚 Publications & Code

Papers from VIP-LAB, newest first. Code is released here as each paper is published. 연구실 논문 목록입니다. 논문 게재에 맞춰 코드를 순차적으로 공개하고 있습니다.

2026

Paper Venue Code
Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop
Y. Cheong, J. An
ICRA 2026 GA-PointDrop
OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth
J. Cho, J. An
ICRA 2026 OASIS-DC
Enhancing Group Attention for Off-Road Semantic Segmentation via Transition-Aware Refinement
S. Choi, J. An
IEEE Signal Processing Letters EGFormer
A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation
S. Choi, J. An
Applied Sciences CSTR

2025

Paper Venue Code
GPT-4off: On-Board Traversability Probability Estimation for Off-Road Driving via GPT Knowledge Distillation
N. Kim, S. Choi, S. Choi, Y. Lee, Y. Cheong, J. An
Applied Sciences GPT-4off

2024

Paper Venue Code
Multisensor Feature Selection for Maritime Target Estimation
S. Choi, J. An
Electronics
Improving Visual Pedestrian Attributes Discernment With Textual Reconstruction
Y. Lee, J. Kim, J. Cho, J. An
IEEE Access
Effective Denoising Algorithms for Converting Indoor Blueprints Using a 3D Laser Scanner
S. Yoon, S. Choi, J. An
Electronics
Route Positioning System for Campus Shuttle Bus Service Using a Single Camera
J. An
Electronics MoodangE-Tracking

2023 and earlier

Paper Venue Code
Knowledge Distillation for Traversable Region Detection of LiDAR Scan in Off-Road Environments
N. Kim, J. An
Sensors, 2023
Traversable Region Detection and Tracking for a Sparse 3D Laser Scanner for Off-Road Environments Using Range Images
J. An
Sensors, 2023
A Lane-level Road Marking Map using a Monocular Camera
W. Jang, J. Hyun, J. An, M. Cho, E. Kim
IEEE/CAA J. Automatica Sinica, 2022
Novel Vehicle Bounding Box Tracking Using a Low-End 3D Laser Scanner
J. An, E. Kim
IEEE T-ITS, 2021
A New Contour-Based Approach to Moving Object Detection and Tracking Using a Low-end 3D Laser Scanner
J. An, B. Choi, H. Kim, E. Kim
IEEE T-VT, 2019

📖 Full publication list → Google Scholar


🛠️ Systems & Tools

Reusable code from our platforms and field experiments. 연구실 플랫폼과 실험에서 축적된 재사용 가능한 코드입니다.

Repository Description
PointPillars-Xavier PointPillars 3D object detection deployed on NVIDIA Jetson Xavier
LeGO-LOAM-Pole Pole-feature-based LiDAR SLAM
2D-Map-Making 2D occupancy map generation utilities

📝 적용 시 확인할 것

  • OASIS-DC 링크는 학생 이전이 끝나야 연결됩니다. 그 전까지 404이니, 신경 쓰이시면 해당 줄의 코드 칸을 공개 예정 으로 바꿔두었다가 이전 후 링크로 교체하세요.
  • YOLOv12-Distillation은 넣지 않았습니다. 심사 중이라 게재 확정 후 2026 표에 한 줄 추가하시면 됩니다.
  • 코드 없는 논문에 를 남겨둔 이유 — 빈칸보다 "코드가 없다"가 명시되는 편이 낫고, 나중에 공개할 때 채워 넣을 자리가 됩니다. 부담스러우시면 코드 있는 논문만 남기고 나머지 행은 지우셔도 됩니다.|

🤝 Join Us

We are looking for self-motivated students interested in autonomous driving, robot perception, and machine learning. Graduate applicants, undergraduate researchers, and visiting students are all welcome.

자율주행·로봇 인지·기계학습에 관심 있는 학생을 기다립니다. 대학원 진학, 학부연구생, 개별연구 모두 문의 가능합니다. 이력서와 성적증명서를 아래 메일로 보내주세요.

📮 jhonghyun@gachon.ac.kr


© Vehicle Intelligence & Perception Laboratory, Gachon University

Popular repositories Loading

  1. LeGO-LOAM-Pole LeGO-LOAM-Pole Public

    Forked from VIPLabGachon/LeGO_LOAM_Pole

    폴(pole) 특징 기반 LiDAR SLAM

    Makefile 1

  2. 2D-Map-Making 2D-Map-Making Public

    Forked from VIPLabGachon/2dMapMaking

    2D 지도 생성 유틸리티

    C++ 1

  3. MoodangE-Tracking MoodangE-Tracking Public

    Forked from VIPLabGachon/MoodangE_tracking

    캠퍼스 자율주행 셔틀 추적 시스템

    Python 1

  4. PointPillars-Xavier PointPillars-Xavier Public

    Forked from VIPLabGachon/PointPillars-on-Xavier

    PointPillars 기반 LiDAR 3D 객체 탐지의 Jetson Xavier 임베디드 배포

    1

  5. GPT-4off GPT-4off Public

    Forked from VIPLabGachon/GPT4off

    GPT-4off: On-Board Traversability Probability Estimation (Applied Sciences 2025)

    1

  6. CSTR CSTR Public

    Forked from sk950324/CSTR-Cross-Scale-Token-Refinement-with-Gated-Structural-Injection-for-Off-Road-Segmentation

    A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation (Applied Sciences 2026)

    Python 1

Repositories

Showing 10 of 10 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…