Eungchan Kim
Papers
1
Total Citations
36
H-Index
1
About
Eungchan Kim is a researcher advancing the field of computer vision and agricultural automation, with a primary focus on amodal segmentation and its application to complex, real-world occlusion problems. Their most notable contribution is the pioneering work on applying amodal segmentation to cucumber detection and occlusion recovery, a challenge critical for robotic harvesting in dense foliage. In their 2023 paper, "Application of amodal segmentation on cucumber segmentation and occlusion recovery," which has garnered 36 citations, Kim demonstrated how deep learning models can infer the full shape of partially hidden crops, enabling more reliable fruit localization. This work bridges the gap between theoretical computer vision and practical agricultural robotics, offering a scalable solution for yield estimation and automated picking. By tackling occlusion—a persistent bottleneck in field robotics—Kim’s research has direct implications for reducing labor costs and improving food supply chain efficiency. Their contributions are particularly impactful for students and researchers interested in the intersection of AI, perception, and sustainable agriculture, showcasing how cutting-edge segmentation techniques can solve tangible, high-stakes problems in natural environments.
Research Focus
Key Achievements
Top Papers
- 1