Jianfeng Han

Papers

Total Citations

115

H-Index

About

Jianfeng Han is a leading researcher in computer vision and precision agriculture, specializing in deep learning-based object detection for complex agricultural environments. His most impactful work, "DSE-YOLO: Detail Semantics Enhancement YOLO for Multi-Stage Strawberry Detection" (2022), has garnered 115 citations, establishing a new benchmark for fine-grained fruit detection. Han's major contribution lies in developing the DSE-YOLO architecture, which enhances the standard YOLO framework with detail semantics modules that capture subtle visual cues—such as color gradients and occluded edges—critical for distinguishing strawberries at different ripeness stages. This innovation directly addresses the challenge of detecting partially obscured or overlapping fruits in natural field conditions, achieving superior accuracy over conventional detectors. Beyond this flagship work, Han's research integrates attention mechanisms and multi-scale feature fusion to improve real-time performance in robotic harvesting systems. His work has practical implications for automated agriculture, reducing labor costs and improving yield estimation. With a growing citation record and a focus on bridging computer vision theory with agricultural robotics, Han is recognized as a key contributor to the next generation of intelligent farming technologies.