Decong Zheng
Papers
2
Total Citations
69
H-Index
2
About
Decong Zheng is a researcher advancing the intersection of computer vision and precision agriculture, with a primary focus on developing lightweight, real-time object detection models for complex field environments. His work addresses critical challenges in smart farming, particularly the need for high-performance yet computationally efficient algorithms that can operate on resource-constrained hardware. Zheng’s major contributions include the YOLOv5-ASFF framework for multistage strawberry detection, which enhances accuracy in cluttered agricultural settings, and the YOLOv8-ECFS model for weed species detection in soybean fields, achieving robust performance with reduced computational overhead. His most-cited paper, “YOLOv5-ASFF: A Multistage Strawberry Detection Algorithm Based on Improved YOLOv5” (2023, 40 citations), demonstrates the practical application of deep learning to automate fruit ripeness assessment, while his 2024 work on YOLOv8-ECFS (29 citations) further refines lightweight architectures for weed management. By prioritizing model efficiency without sacrificing detection accuracy, Zheng’s research directly supports the deployment of intelligent monitoring systems in agriculture, contributing to sustainable farming practices and reduced labor dependency. His work is particularly notable for bridging the gap between cutting-edge AI and real-world agricultural constraints.
Research Focus
Key Achievements
Top Papers
- 1
- 2