Zhenfeng Yi
Papers
1
Total Citations
12
H-Index
1
About
Zhenfeng Yi is a researcher at the forefront of agricultural automation and computer vision, with a focused expertise in deep learning-based object detection for precision harvesting. Their most-cited work, "Lightweight-Improved YOLOv5s Model for Grape Fruit and Stem Recognition" (2024, 12 citations), addresses a critical bottleneck in mechanized harvesting: the accurate, real-time identification of fruits and stems. Yi’s major contribution lies in optimizing the YOLOv5s architecture to create a lightweight model that balances high detection accuracy with computational efficiency, making it deployable on resource-constrained hardware for field applications. This innovation directly tackles the dual challenges of high labor costs and low harvesting efficiency in agriculture. By enhancing the model’s ability to distinguish grape bunches from stems in complex orchard environments, Yi’s work provides a practical pathway toward fully autonomous harvesting systems. Their research not only advances the state-of-the-art in agricultural robotics but also demonstrates a clear commitment to translating AI methods into tangible solutions for food production. For students and researchers, Yi exemplifies how targeted improvements to established models can yield impactful, real-world results in niche but vital domains.
Research Focus
Key Achievements
Top Papers
- 1Lightweight-Improved YOLOv5s Model for Grape Fruit and Stem Recognition12 citations · 2024