Qiming Song
Papers
1
Total Citations
12
H-Index
1
About
Qiming Song is a researcher whose work sits at the intersection of computer vision, agricultural automation, and edge computing. His primary focus is on developing lightweight, high-precision object detection models optimized for deployment on resource-constrained embedded devices, with a particular emphasis on agricultural applications. His most cited paper, "A Lightweight and High-Precision Passion Fruit YOLO Detection Model for Deployment in Embedded Devices" (2024, 12 citations), exemplifies this contribution. In this work, Song addresses the critical challenge of real-time fruit detection in complex, real-world orchard environments—including backlighting, occlusion, and variable weather—by proposing a modified YOLOv5 architecture. By replacing the standard backbone with a more efficient alternative, his model achieves significant reductions in detection time while maintaining or improving average precision, making it viable for low-power hardware. This innovation has direct implications for smart agriculture, enabling cost-effective, real-time monitoring and harvesting systems. Song’s research bridges the gap between state-of-the-art deep learning and practical, deployable solutions, marking him as a promising voice in the field of embedded vision for precision agriculture.
Research Focus
Key Achievements
Top Papers
- 1