Xunhui Liu
Papers
1
Total Citations
1
H-Index
1
About
Xunhui Liu is a researcher at the forefront of precision agriculture and computer vision, with a focused expertise in deep learning-based phenotyping and plant growth monitoring. Liu’s most notable contribution is the development of YOLO-RCMC, an advanced object detection model that significantly improves the automated detection of strawberry bloom phenology. By introducing a novel Reparameterized Convolution Module (RCM) and a tailored RCM-variant, Liu’s work bridges the gap between flower opening scales and phenological stages, enabling accurate, multi-angle detection of flower development. This achievement not only enhances the efficiency of yield prediction and pollination management but also sets a new benchmark for model accuracy, efficiency, and size in agricultural AI. With a growing citation impact, Liu’s research is pivotal for integrating smart farming technologies with real-time crop monitoring. Their work stands out for its practical application in controlled environments and open fields, offering a scalable solution for high-throughput phenotyping. Liu’s innovative approach to linking morphological traits with machine learning marks a significant step forward in sustainable agriculture and digital phenotyping.
Research Focus
Key Achievements
Top Papers
- 1