I am a postdoctoral researcher at the Department of Electronics and Informatics at Vrije Universiteit Brussel. Previously, I completed my Ph.D. research, titled “Deep-Learning-Based Multi-Modal Fusion for Traffic Image Data Processing,” under the supervision of Prof. Dr. Ir. Adrian Munteanu. During my Ph.D., I participated in research projects in collaborations with Macq S.A./N.V. and FLIR. In 2018, I worked as a computer vision researcher at the autonomous driving startup FABU. I hold a master’s degree in Applied Computer Science from Vrije Universiteit Brussel and a bachelor’s degree in Computer Science from Xidian University.
My research interests include but not limited to deep learning, object pose estimation, image semantic segmentation, 2D/3D vision, and domain adaptation. During my Ph.D., my research mainly focus on deep learning based multi-modal data fusion for traffic relevant tasks.
📖 Educations
- 2019.07 - 2024.06, Vrije Universiteit Brussel, Ph.D., with the highest distinction.
- 2016.09 - 2018.06, Vrije Universiteit Brussel, Master, with great distinction.
- 2013.08 - 2017.06, Xidian University, Bachelor, ranked 4/440.
🧗🏻♀️ Experience
- 2024.06 - Now, Post-Doc, Vrije Universiteit Brussel.
- 2019.07 - 2024.06, Ph.D. researcher, Vrije Universiteit Brussel.
- 2018.08 - 2019.05, R&D engineer, FABU Technology Co. Ltd..
- 2017.06 - 2018.06, Student research assistant, Vrije Universiteit Brussel.
- 2016.09 - 2017.06, Extrange student, Vrije Universiteit Brussel.
📝 Publications
W6DNet: Weakly-supervised Domain Adaptation for Monocular Vehicle 6D Pose Estimation with 3D Priors and Synthetic Data
Yangxintong Lyu, Remco Royen, Adrian Munteanu
IEEE Transactions on Instrumentation and Measurement
Mono6D: Monocular vehicle 6D pose estimation with 3D priors
Yangxintong Lyu, Remco Royen, Adrian Munteanu
IEEE International Conference on Image Processing (ICIP)
Multi-modal neural networks with multi-scale RGB-T fusion for semantic segmentation
Yangxintong Lyu, Ionut Schiopu, Adrian Munteanu
IET Electronics Letters
Consistent video projection on curved displays
Yangxintong Lyu, Shao-Ping Lu, Quentin Bolsee, Adrian Munteanu
Elsvier Signal Processing: Image Communication
Framework for Vehicle Make and Model Recognition—A New Large-Scale Dataset and an Efficient Two-Branch–Two-Stage Deep Learning Architecture
Yangxintong Lyu, Ionut Schiopu, Bruno Cornelis, Adrian Munteanu
MDPI Sensors
-
DeepKalPose: An enhanced deep‐learning Kalman filter for temporally consistent monocular vehicle pose estimation, Leandro Di Bella, Yangxintong Lyu, Adrian Munteanu, Electronics Letters
-
STRADA: Spatial-Temporal Dashboard for traffic forecasting, Seyed Mohamad Mohadas, Yangxintong Lyu, Bruno Cornelis, Adrian Munteanu, 25th IEEE International Conference on Mobile Data Management (MDM) 2024
-
MonoKalman: Monocular Vehicle Pose Estimation with Kalman Filter-based temporal consistency, Leandro Di Bella, Yangxintong Lyu, Bruno Cornelis, Adrian Munteanu, 25th IEEE International Conference on Mobile Data Management (MDM) 2024
-
Mono6D++: Learning Point Cloud Visibility for 3D Prior-based Vehicle 6D Pose Estimation, Yangxintong Lyu, Olivier Ducastel, Remco Royen, Adrian Munteanu, 11th European Workshop on Visual Information Processing (EUVIP) 2023
-
Occlusion-Aware 3D Priors for Deep Learning-Based Applications, Olivier Ducastel, Yangxintong Lyu, Leon Denis, Adrian Munteanu, IEEE International Workshop on Multimedia Signal Processing (MMSP) 2023
🎖 Honors and Awards
- National Scholarship, awarded by the Chinese Ministry of Education (top 1%).
- The 3rd prize in Shaanxi province, ACM/ICPC.
- The 2nd prize in Shaanxi province, Contemporary Undergraduate Mathematical Contest in Modeling.
🌟 Services
- Reviewer: IEEE TIP (IF: 10.8), EAAI (IF: 8.0), CVPR and ICIP.
- Teaching assistant (2020 - now): Image Processing.
- Co-supervisor: 4 master theses.