Ghiseok Kim
Papers
1
Total Citations
36
H-Index
1
About
Ghiseok Kim is a leading researcher in agricultural computer vision, specializing in advanced image analysis techniques for crop monitoring and automation. His work focuses on overcoming critical challenges in precision agriculture, particularly the segmentation and recovery of occluded objects in natural field conditions. Kim’s most cited paper, “Application of amodal segmentation on cucumber segmentation and occlusion recovery” (2023), has garnered 36 citations, establishing a foundational method for inferring the full shape of partially hidden crops. This contribution directly addresses a major bottleneck in robotic harvesting and yield estimation, enabling more robust perception systems. By integrating amodal segmentation—a technique typically used in general computer vision—into agricultural contexts, Kim has demonstrated how cutting-edge AI can be adapted for real-world farming needs. His research not only advances the theoretical understanding of occlusion handling but also provides practical tools for improving the accuracy of automated agricultural systems. With a growing citation record, Kim is recognized for bridging the gap between computer vision research and sustainable agricultural technology, making his work essential reading for students and researchers in agri-robotics and smart farming.
Research Focus
Key Achievements
Top Papers
- 1