QiMing Song
Papers
1
Total Citations
14
H-Index
1
About
QiMing Song is a leading researcher in agricultural artificial intelligence and embedded computer vision, with a focus on developing lightweight, high-precision detection models for fruit and crop monitoring. His most-cited work, "A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices" (2024, 14 citations), addresses the critical challenge of real-time fruit detection under complex environmental conditions—including backlight, occlusion, overlap, and varying weather. By replacing the backbone network of YOLOv5 with a more efficient architecture, Song achieved significant reductions in detection time while maintaining high average precision, enabling deployment on resource-constrained embedded devices. This contribution bridges the gap between deep learning performance and practical agricultural applications, where edge computing is essential. Song’s research has direct implications for smart farming, automated harvesting, and precision agriculture, offering scalable solutions that balance accuracy with computational efficiency. His work is widely cited by peers developing real-time detection systems for specialty crops, and he continues to advance the field of lightweight neural networks for agricultural robotics.
Research Focus
Key Achievements
Top Papers
- 1