Papers

4

Total Citations

95

H-Index

4

About

Junduan Huang is a researcher at the forefront of agricultural automation, specializing in computer vision and deep learning for precision horticulture. His work focuses on developing lightweight, edge-deployable AI models that enable real-time fruit detection and harvesting in complex orchard environments. Huang’s most significant contributions include the creation of an improved YOLOv8 architecture that simultaneously performs object detection and instance segmentation for mango picking-point localization—a breakthrough that has garnered 44 citations. He further advanced this line of research by engineering a system capable of detecting both fruits and fruiting stems in mango trees using an optimized YOLOv8 model deployed on edge devices, earning 38 citations. More recently, Huang has extended his methodology to passion fruit cultivation, designing a lightweight deep learning model for detecting green passion fruits in natural, unstructured orchards. His cumulative work, with over 95 citations, demonstrates a clear trajectory toward practical, low-latency solutions for automated harvesting. By prioritizing edge computing efficiency without sacrificing accuracy, Huang is helping bridge the gap between agricultural robotics research and real-world farm deployment.

Research Focus

Key Achievements

4
H-Index
4
Papers
95
Total Citations
24
Avg Citations/Paper
🏆 Most Cited Paper
Positioning of mango picking point using an improved YOLOv8 architecture with object detection and instance segmentation
44 citations · 2024
📈 Most Prolific Year: 2024 (3 Papers)
🤝 Key Collaborators: 16
🏛 Institutions: Guangxi University, South China Normal University, South China University of Technology

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 14 days ago