Wanpeng Fan
Papers
2
Total Citations
33
H-Index
2
About
Wanpeng Fan is a researcher advancing the field of agricultural computer vision, with a focused expertise in deep learning-based instance segmentation for complex natural environments. His key research area centers on improving object detection and segmentation models—specifically variants of the YOLO architecture—to address the challenges of automated agricultural monitoring. Fan’s major contributions lie in adapting state-of-the-art models like YOLOv8 for the precise detection and segmentation of lotus seedpods within challenging pond environments, where factors such as insignificant phenotypic differences, variable lighting, and overlapping foliage complicate traditional computer vision approaches. His work directly supports critical agricultural tasks, including yield prediction and picking pose estimation for lotus seedpods. With his most cited papers, "An Improved YOLOv8-Seg Model for Lotus Seedpod Instance Segmentation in the Lotus Pond Environment" (2024, 18 citations) and its companion study (15 citations), Fan has demonstrated significant early impact in a specialized domain. These publications represent notable achievements in applying deep learning to solve real-world agricultural problems, establishing a foundation for more robust and automated crop monitoring systems in aquatic farming environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2