Dongkyu Kim
Papers
1
Total Citations
6
H-Index
1
About
Dongkyu Kim is a researcher focused on advancing real-time computer vision for resource-constrained edge devices. His work centers on making deep learning-based object detection practical and efficient for intelligent platforms such as drones, robots, and autonomous vehicles. In his most-cited paper, "Real-time object detection using a domain-based transfer learning method for resource-constrained edge devices" (2023, 6 citations), Kim introduces a novel transfer learning approach that enables high-performance object detection to run in real time on devices with limited computational power. This contribution directly addresses a critical bottleneck in deploying AI on edge hardware, balancing accuracy with speed. Kim’s research is particularly impactful for applications requiring on-device intelligence without cloud dependency, such as autonomous navigation and surveillance. His work demonstrates a clear understanding of both algorithmic efficiency and practical deployment challenges, marking him as a promising contributor to the field of embedded computer vision and edge AI.
Research Focus
Key Achievements
Top Papers
- 1