Xuefeng Ren
Papers
3
Total Citations
48
H-Index
3
About
Xuefeng Ren is a leading researcher in agricultural AI and computer vision, specializing in deep learning-based fruit ripeness detection for smart farming. His work focuses on developing high-precision, real-time object detection models tailored to complex farmland environments, addressing critical challenges in automated agriculture. Ren's most impactful contribution is his 2024 study upgrading the Swin-B transformer with a task-aligned one-stage detection mechanism for accurately identifying ripe strawberries, which has garnered 37 citations. This work significantly improves detection accuracy in challenging conditions. He further advanced the field with a real-time lightweight framework based on YOLO11, deployable on edge computing platforms (2025, 6 citations), enabling practical, low-latency applications. Ren also tackled the problem of distinguishing difficulty imbalances in strawberry ripeness instances within complex scenes (2024, 5 citations), proposing a novel hybrid attention mechanism with a partial convolution-based compact inverted block to reduce false positives and missing rates. His research bridges cutting-edge transformer and lightweight CNN architectures, offering scalable solutions for precision agriculture.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3