Skip to content
View jhonghyunAn's full-sized avatar

Block or report jhonghyunAn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jhonghyunAn/README.md

Hi, I'm Jhonghyun An (안종현) 👋

Associate Professor, Department of AI-Software, Gachon University (Mar. 2022 – present) Director, VIP-LAB — Vehicle Intelligence & Perception Laboratory · @ORG_NAME

Ground-to-Air Robust Robot Vision — perception that keeps working off-road, in adverse weather, and from the air.

ORCID Google Scholar Homepage YouTube Email


🔬 Research Interests

  • Multi-sensor fusion — LiDAR × Camera × Radar × Thermal (EO/IR)
  • 3D perception — object detection & tracking, semantic segmentation, depth completion, traversability estimation
  • Robust perception in the wild — off-road / unstructured terrain, adverse weather, domain adaptation
  • Efficient deep learning — knowledge distillation, pruning, NAS, quantization for on-device & edge AI
  • Physical AI — perception–action models for ground vehicles, UAVs, and field robots
Low-end 3D LiDAR perception  →  Multi-sensor fusion & deep learning  →  Ground-to-Air Robust Robot Vision

🎓 Background

2022 – present Associate Professor, Dept. of AI-Software, Gachon University
2020 – 2022 Senior Researcher, Agency for Defense Development (ADD) — Unmanned Ground System PMO Team 1
2013 – 2020 Ph.D., Electrical & Electronic Engineering, Yonsei University (Computational Intelligence Lab, advisor: Prof. Euntai Kim)
2008 – 2012 B.S., Electrical & Electronic Engineering, Yonsei University

Teaching — Deep Learning · Data Structures · Probabilistic Robotics Editorial / Review — Editor, Journal of KIIS · Reviewer for IEEE T-VT, IV, ITSC, IJCAS · Guest Editor, Applied Sciences (Special Issue on detection & tracking for autonomous driving)

📄 Selected Publications

Corresponding author on all VIP-LAB publications (2022–present).

Journals

  • S. Choi, J. An, "A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation," Applied Sciences, 2026.
  • N. Kim, S. Choi, S. Choi, Y. Lee, Y. Cheong, J. An, "GPT-4off: On-Board Traversability Probability Estimation for Off-Road Driving via GPT Knowledge Distillation," Applied Sciences, 2025.
  • Y. Lee, J. Kim, J. Cho, J. An, "Improving Visual Pedestrian Attributes Discernment With Textual Reconstruction," IEEE Access, 2024.
  • N. Kim, J. An, "Knowledge Distillation for Traversable Region Detection of LiDAR Scan in Off-Road Environments," Sensors, 2023.
  • W. Jang, J. Hyun, J. An, M. Cho, E. Kim, "A Lane-level Road Marking Map using a Monocular Camera," IEEE/CAA Journal of Automatica Sinica, 2022.
  • J. An, E. Kim, "Novel Vehicle Bounding Box Tracking Using a Low-End 3D Laser Scanner," IEEE Trans. on Intelligent Transportation Systems (T-ITS), 2021.
  • J. An, B. Choi, H. Kim, E. Kim, "A New Contour-Based Approach to Moving Object Detection and Tracking Using a Low-end 3D Laser Scanner," IEEE Trans. on Vehicular Technology (T-VT), 2019.

Conferences

  • Y. Cheong, J. An, "Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop," ICRA 2026, Vienna.
  • J. Cho, J. An, "OASIS-DC: Generalizable Depth Completion via Output-level Alignment of Sparse-Integrated Monocular Pseudo Depth," ICRA 2026, Vienna.
  • W. Jang, J. An, S. Lee, M. Cho, M. Sun, E. Kim, "Road Lane Semantic Segmentation for High Definition Map," IEEE IV 2018.
  • J. An, B. Choi, T. Hwang, E. Kim, "A Novel Rear-End Collision Warning System Using Neural Network Ensemble," IEEE IV 2016.

📚 Full list → Google Scholar · ORCID 🎥 Demo videos → VIP-LAB on YouTube

🛠️ Ongoing Projects (PI)

  • EO/IR payload under 500 g for fixed-/rotary-wing UAVs — edge-optimized small-object detection for aerial scenes · EOST, 2025–2027
  • Intelligent 3-axis stabilized EO/IR integrated system — robust small-object detection & tracking under platform motion · EOST, 2024–2028
  • SDV-based automotive SW platform linked to an AI framework — pruning, distillation, NAS, and quantization for real-time on-device perception · IITP, 2024–2027
  • Wide-area semantic mapping with multi-robot systems (open-field & wilderness) — 3D point-cloud semantic segmentation, crowdsourced map update & change detection · TIPA, 2025–2027
  • AI for battlefield situation awareness — lightweight thermal object detection with dual-teacher (RGB–thermal) distillation and super-resolution on embedded boards · Hyundai Rotem, 2024–2026

Past industry & government partners: NRF · LIG Nex1 · Mobiltech · Neubility · Hyundai Motor Group · Hyundai Mobis · Hyundai NGV · Korea Railroad Research Institute

🏅 Awards & Patents

  • Outstanding Research Award, ICROS 2020 (35th Annual Conference)
  • US Patent US9827994 — Writing an occupancy grid map in a sensor-centered coordinate system using a laser scanner (2017), + 2 registered and 4 filed KR patents

💻 Skills

Python C/C++ MATLAB PyTorch ROS

🤝 Get in Touch

Open to collaboration on autonomous driving perception, robot vision, UAV / EO-IR systems, and industry–academia projects. 📮 jhonghyun@gachon.ac.kr · 📍 Seongnam, Republic of Korea 🔗 Lab homepage · YouTube · Google Scholar


🇰🇷 가천대학교 AI·소프트웨어학부 / VIP-LAB (차량지능 및 인지 연구실) — 대학원생·학부연구생 상시 모집 중입니다.

Pinned Loading

  1. VIPLAB-Gachon/CSTR VIPLAB-Gachon/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

  2. VIPLAB-Gachon/EGFormer VIPLAB-Gachon/EGFormer Public

    Forked from sk950324/EGFormer

    Enhancing Group Attention for Off-Road Semantic Segmentation via Transition-Aware Refinement (IEEE SPL 2026)

    Python

  3. VIPLAB-Gachon/GA-PointDrop VIPLAB-Gachon/GA-PointDrop Public

    Forked from YoungJae1559/GA-PointDrop

    Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop (ICRA 2026)

    Python

  4. VIPLAB-Gachon/YOLOv12-Distillation VIPLAB-Gachon/YOLOv12-Distillation Public

    Forked from YoungJae1559/YOLOv12-Distillation

    Cross-Attention 및 Frequency-Decoupled 기법 기반 YOLOv12 Feature/Head Knowledge Distillation을 통한 모델 경량화(Model Compression)

    Python