Junhyuk Hyun

Papers

Total Citations

H-Index

About

Junhyuk Hyun is a researcher advancing the field of real-time semantic segmentation for mobile robotics and autonomous systems. His primary research areas include deep learning-based computer vision, semantic segmentation, and robotic perception, with a focus on enabling efficient, real-time scene understanding for wheeled mobile robots. Hyun’s major contribution is the development of the Adjacent Feature Propagation Network (AFPNet), a novel architecture designed for high-speed semantic segmentation without sacrificing accuracy. This work, which has garnered 20 citations, addresses a critical bottleneck in deploying deep learning models on resource-constrained robotic platforms. Additionally, his research on street floor segmentation (8 citations) introduces a specialized task for urban navigation, enabling robots to identify traversable surfaces and adapt their control strategies accordingly. By tackling the challenges of real-time processing and domain-specific segmentation, Hyun’s work directly supports the practical deployment of autonomous vehicles and mobile robots in complex, dynamic environments. His contributions are particularly notable for bridging the gap between state-of-the-art deep learning and the real-time constraints of embodied AI systems.