Jing Dong

Papers

2

Total Citations

93

H-Index

2

About

Jing Dong is a researcher specializing in computer vision, deep learning, and agricultural robotics, with a particular focus on applying advanced neural network architectures to precision horticulture and smart greenhouse technologies. Their work centers on developing intelligent systems that enable autonomous robots to monitor, identify, and interact with crops throughout their growth cycles. Dong's most notable contribution is the development of a YOLO-DeepSORT tracking network, tailored for tomato detection and counting across different growth stages. By integrating ShuffleNetV2 and the Convolutional Block Attention Module (CBAM) into the YOLOv5s framework, this work achieved robust performance for yield prediction in dynamic cultivation environments — garnering 76 citations since its 2022 publication and signaling strong adoption within the agricultural AI community. Complementing this, Dong's research on flowering phase detection introduces a neural network enhanced with attention mechanisms and additional feature fusion layers, addressing the challenging problem of pollination robot guidance in complex greenhouse lighting conditions. Taken together, Dong's work represents a meaningful bridge between state-of-the-art computer vision techniques and real-world agricultural automation, contributing practical tools that support smarter, more efficient crop management — an area of rapidly growing importance as the agricultural sector embraces robotics and AI-driven solutions.

Research Focus

Key Achievements

2
H-Index
2
Papers
93
Total Citations
47
Avg Citations/Paper
🏆 Most Cited Paper
Tracking and Counting of Tomato at Different Growth Period Using an Improving YOLO-Deepsort Network for Inspection Robot
76 citations · 2022
📈 Most Prolific Year: 2022 (2 Papers)
🤝 Key Collaborators: 12

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago