Huibo Song
Papers
1
Total Citations
2
H-Index
1
About
Huibo Song is a leading researcher in agricultural computer vision and precision phenotyping, with a primary focus on intelligent crop monitoring and yield estimation. Her work centers on developing advanced deep learning and transformer-based models for multi-object tracking and counting in complex field environments. Song’s most cited paper, “Multi-Object Tracking for Cotton Boll Counting in Ground Videos Based on Transformer” (2024), introduces a novel framework that leverages attention mechanisms to accurately track and enumerate cotton bolls from ground-level video data, addressing a critical bottleneck in high-throughput phenotyping. This contribution directly supports breeders and growers by providing automated, non-destructive insights into plant genetic and physiological growth mechanisms, enabling more informed crop management decisions. By bridging computer vision with agricultural science, Song’s research has significant implications for improving yield prediction and resource allocation in cotton production. Her work exemplifies the growing impact of AI in agriculture, with her transformer-based approach setting a new standard for precision and scalability in field-based phenotyping tasks.
Research Focus
Key Achievements
Top Papers
- 1