Jingfan Liu

Papers

Total Citations

H-Index

About

Jingfan Liu is a leading researcher in agricultural robotics and computer vision, with a focus on intelligent harvesting systems. Their work centers on developing advanced deep learning methods for real-time fruit detection and robotic manipulation in complex orchard environments. Liu’s most impactful contribution is the comprehensive review "The Vision-Based Target Recognition, Localization, and Control for Harvesting Robots: A Review" (2023), which has garnered 47 citations and serves as a foundational reference for the field, synthesizing decades of progress in visual perception and robotic control. Building on this, Liu proposed YOLOv5s-BC, an improved YOLOv5s-based architecture for real-time apple detection, published in 2023 and 2024. This method integrates a coordinate attention (CA) block to enhance feature extraction, significantly boosting detection accuracy and speed under challenging conditions like occlusion and variable lighting. With over 69 total citations, Liu’s work directly addresses critical bottlenecks in agricultural automation, enabling more reliable and efficient harvesting robots. Their research is widely recognized for bridging the gap between computer vision theory and practical deployment, making Liu a key figure in the advancement of precision agriculture and smart farming technologies.