Zefeng Shi
Papers
2
Total Citations
13
H-Index
2
About
Zefeng Shi is a researcher at the forefront of agricultural robotics and intelligent perception, specializing in computer vision and deep learning for autonomous systems. His work focuses on developing robust detection and localization algorithms that enable mobile robots to operate effectively in complex, unstructured environments—from indoor settings to natural orchards. Shi’s major contributions include pioneering the application of improved YOLOv5 for indoor target detection and localization, achieving high accuracy in dynamic, real-time scenarios. He also advanced fruit detection in agriculture by integrating Faster R-CNN with Feature Pyramid Networks (FPN) to address the significant challenge of identifying pecan fruits against similarly colored foliage and variable lighting. His most-cited papers have accumulated over 13 citations, reflecting growing interest in his practical, field-ready solutions. Notably, his research on pecan detection directly tackles a critical bottleneck in robotic harvesting, offering a vision system that can distinguish subtle color differences and handle complex backgrounds. Shi’s work is instrumental in bridging the gap between laboratory algorithms and real-world agricultural automation, making him a key contributor to the future of intelligent picking robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2