Lijun Cheng
Papers
1
Total Citations
2
H-Index
1
About
Lijun Cheng is a leading researcher in computer vision and agricultural automation, with a primary focus on developing lightweight, high-performance object detection models for complex environments. Their most notable contribution is the DSW-YOLO model, an innovative improvement on YOLOv10n designed specifically for green pepper detection in challenging field conditions. By designing the DWRR block and systematically comparing mainstream lightweight architectures—including YOLOv5n, YOLOv6n, YOLOv8n, YOLOv9t, and YOLOv10n—Cheng achieved a breakthrough in balancing detection accuracy with computational efficiency. This work, published in 2025 and already garnering 2 citations, addresses critical challenges in precision agriculture, such as occluded targets and variable lighting. Cheng’s research directly impacts smart farming by enabling real-time, resource-efficient crop monitoring, reducing the gap between laboratory models and practical deployment. Their methodological rigor in benchmarking and model optimization sets a standard for future lightweight detection systems, making their work essential reading for researchers in agricultural AI and embedded vision applications.
Research Focus
Key Achievements
Top Papers
- 1DSW-YOLO-Based Green Pepper Detection Method Under Complex Environments2 citations · 2025