Papers
5
Total Citations
81
H-Index
5
About
Rihong Zhang is a leading researcher in agricultural robotics and smart farming, specializing in computer vision and deep learning for automated crop harvesting. Their work focuses on developing lightweight, efficient neural networks for real-time detection and segmentation of fruits and produce in complex, natural environments. Zhang's major contributions include pioneering methods for banana stalk segmentation using multi-feature fusion deep neural networks (22 citations), which enable robots to distinguish stalks from similarly colored leaves and branches. They also advanced tea bud detection in high-density canopies with YOLOX-S, achieving an average precision of 0.87 while processing images in just 17.43 ms (21 citations). Notably, Zhang introduced a deep reinforcement learning approach for inverse kinematics in series-parallel hybrid banana-harvesting robots (16 citations), solving a previously intractable control problem. Their lightweight pineapple detection model, MSGV-YOLOv7 (13 citations), further demonstrates their commitment to deployable, real-time solutions. With a remote configurable image acquisition robot for smart agriculture (9 citations), Zhang has laid foundational work for field-deployable systems. Their research directly addresses the challenges of automated picking in orchards and high-density canopies, making significant strides toward practical, intelligent agricultural robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4MSGV-YOLOv7: A Lightweight Pineapple Detection Method13 citations · 2023
- 5