Sijian Wen
Papers
1
Total Citations
33
H-Index
1
About
Sijian Wen is a rising researcher at the forefront of agricultural artificial intelligence, with a focused expertise in deep learning-based fruit detection and precision agriculture. His most impactful work centers on overcoming the challenges of automated fruit recognition in complex, real-world orchard environments. Wen's major contribution, the DNE-YOLO method, introduces a novel mist simulation algorithm to generate training data, dramatically improving the robustness of object detection models under adverse conditions like fog, glare, and occlusion. This innovation, published in 2024 and already garnering 33 citations, directly addresses a critical bottleneck in the mechanization and intelligent advancement of apple picking technology. By enabling reliable fruit detection in diverse natural settings, Wen's research provides a foundational tool for the development of autonomous harvesting robots and yield estimation systems. His work stands as a significant step toward bridging the gap between controlled laboratory vision systems and the unpredictable, variable conditions of commercial orchards, marking him as a key contributor to the future of smart agriculture.
Research Focus
Key Achievements
Top Papers
- 1DNE-YOLO: A method for apple fruit detection in Diverse Natural Environments33 citations · 2024