Joong‐won Hwang

Electronics and Telecommunications Research Institute

Papers

Total Citations

H-Index

About

Joong-won Hwang is a researcher focused on advancing object detection for safety-critical applications, particularly in autonomous driving and robotics. His primary research area centers on uncertainty estimation in computer vision, where he addresses the critical challenge of making object detectors reliable in unstable environments plagued by sensor noise and incomplete data. Hwang's major contribution is his work on localization uncertainty estimation for anchor-free object detection, a method that quantifies the confidence of bounding box predictions. This approach directly tackles the limitations of existing detectors, which often fail to account for uncertainty, leading to potential failures in high-stakes systems like surgical robots and self-driving cars. His most cited paper, published in 2023, has garnered 24 citations, reflecting growing interest in robust perception for autonomous systems. By enabling detectors to express when they are uncertain about an object's location, Hwang's research enhances the safety and reliability of AI in real-world deployment. His work bridges the gap between theoretical computer vision and practical engineering, making him a notable contributor to the field of trustworthy AI for autonomous systems.