Suh-Yong Choi

Papers

Total Citations

H-Index

About

Suh-Yong Choi is a researcher focused on advancing artificial intelligence for autonomous systems, particularly in the domain of driving scene understanding. His work centers on leveraging deep neural networks to enhance how machines perceive and interpret complex visual environments, a critical challenge for self-driving vehicles and intelligent robotics. Choi’s most cited paper, “Driving Scene Understanding Using Hybrid Deep Neural Network” (2019, 9 citations), proposes a hybrid architecture that integrates multiple neural network models to improve real-time object recognition and contextual judgment in driving scenes. This work addresses the limitations of conventional vision processing by enabling more meaningful, context-aware AI decisions. In a related study, “Efficient Driving Scene Image Creation Using Deep Neural Network” (2019, 5 citations), he explores generative techniques to synthesize realistic driving images for training machine learning models, tackling data scarcity in autonomous vehicle research. Though his citation counts are modest, Choi’s contributions are foundational to the practical deployment of AI in safety-critical applications, bridging the gap between raw visual data and high-level scene comprehension. His research underscores the importance of hybrid and generative approaches in pushing the boundaries of autonomous perception.