Yingjie Lv

Papers

Total Citations

189

H-Index

About

Yingjie Lv is a leading figure in precision agriculture and computer vision, whose work has fundamentally advanced the automated detection and monitoring of crops in complex field environments. His research centers on deep learning applications for agricultural image analysis, with a particular focus on overcoming challenges posed by varying plant growth stages and unstructured outdoor settings. Lv’s most impactful contribution is the development of an improved Faster R–CNN architecture for maize seedling detection, a breakthrough that achieved robust performance across different growth stages and under diverse, often adverse, field conditions. This seminal 2019 paper has garnered 189 citations, reflecting its widespread adoption as a benchmark for object detection in agricultural robotics and phenotyping. Beyond this core work, Lv has made notable strides in integrating attention mechanisms and multi-scale feature fusion to enhance model accuracy, directly addressing the occlusion and lighting variability that plague real-world deployment. His research not only provides a scalable solution for automated plant counting and health assessment but also lays the groundwork for intelligent farming systems. For students and researchers, Lv’s work exemplifies how tailored deep learning models can bridge the gap between controlled laboratory conditions and the messy reality of agricultural fields.