Fengyang Shangguan
Papers
2
Total Citations
43
H-Index
2
About
Fengyang Shangguan is an emerging researcher specializing in computer vision and intelligent agriculture, with a particular focus on applying deep learning-based object detection to precision farming applications. Their most notable contribution is the development of YOLOv8-CML, a lightweight target detection model designed to identify the ripeness of color-changing melons — a fruit valued for both its ornamental and edible qualities — within smart agricultural environments. By introducing innovations such as a lightweight Faster-Block architecture, Shangguan's work directly addresses critical real-world challenges including slow detection speeds and high deployment costs on agricultural hardware, making advanced AI more accessible for robotic harvesting systems. This research has garnered significant attention, accumulating over 40 citations across its published versions, reflecting its relevance to the rapidly growing field of agricultural automation. Shangguan's work sits at an important intersection of embedded systems optimization and agricultural AI, contributing practical, deployable solutions rather than purely theoretical advances. For students and researchers working on AI-driven precision agriculture or efficient neural network design, Shangguan's research offers a compelling example of how model architecture innovation can translate directly into improved real-world performance.
Research Focus
Key Achievements
Top Papers
- 1
- 2