Moongu Jeon
Papers
7
Total Citations
200
H-Index
4
About
Moongu Jeon is a leading researcher at the intersection of robotics, autonomous driving, and intelligent systems, with a core focus on multi-sensor data fusion and computer vision. His most influential work, "Data fusion of radar and image measurements for multi-object tracking via Kalman filtering" (112 citations), established foundational methods for combining heterogeneous sensor data to achieve robust object tracking—a critical capability for autonomous vehicles. Jeon has also made significant contributions to deep learning-based perception, including vehicle pose detection using region-based convolutional neural networks (22 citations), which advanced practical applications in intelligent transportation and robotics. His research extends to addressing real-world challenges, such as learning to see in adverse weather conditions through disentangled representation learning, and exploring data variance issues in radar-camera fusion for autonomous driving. Beyond perception, Jeon has applied evolutionary algorithms to fuzzy path planning for robot soccer, demonstrating versatility across robotics domains. His work on ICT-enabled TVET education (43 citations) further reflects a broader interest in leveraging technology for societal impact. With a career spanning foundational sensor fusion techniques to cutting-edge deep learning solutions, Jeon’s research continues to shape the reliability and intelligence of autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2ICT Enabled TVET Education: A Systematic Literature Review43 citations · 2021
- 3Vehicle pose detection using region based convolutional neural network22 citations · 2016
- 4
- 5
- 6
- 7Learning to See in the Rain via Disentangled Representation3 citations · 2021