Xinting Ge

Xuzhou Medical College, Shandong Normal University

Papers

Total Citations

H-Index

About

Xinting Ge is a researcher specializing in computer vision and precision agriculture, with a particular focus on developing advanced deep learning methods for fruit detection and segmentation in complex agricultural environments. Their work addresses one of the most pressing challenges in agricultural robotics: enabling fruit-picking robots to accurately identify and localize target fruits under real-world orchard conditions, where variable lighting, occlusion, and overlapping produce make visual recognition exceptionally difficult. Ge's most notable contribution is an optimized Mask RCNN framework designed for accurate segmentation of green fruits in complex orchard settings, which has garnered 45 citations since its publication in 2022, reflecting strong interest from both the robotics and precision agriculture communities. Building on this foundation, Ge introduced FCOS-EAM in 2024, an innovative two-stage detection-then-segmentation pipeline incorporating an edge attention module and box attention merging mechanism specifically engineered to handle overlapping fruit instances — a persistent challenge that prior methods struggled to resolve effectively. Together, these contributions position Ge as an emerging voice in agricultural AI, advancing the practical deployment of autonomous harvesting robots and demonstrating a consistent commitment to bridging cutting-edge computer vision research with real-world agricultural applications.