Qinghui Zhang

Henan University of Technology, Southwest Forestry University

Papers

Total Citations

H-Index

About

Qinghui Zhang is a rising researcher at the forefront of intelligent robotics and agricultural automation, with key contributions in multimodal perception, deep learning, and structured light imaging. Zhang’s work bridges the gap between advanced computer vision and practical robotic applications, particularly in challenging environments involving high-reflectivity objects and precision agriculture. Their most notable contribution is the development of a deep diffusion learning framework for mutual-reflective structured light patterns, enabling simultaneous 3D imaging of multiple objects—a critical advancement for robot operations in intelligent manufacturing. This work has already garnered 6 citations shortly after its 2024 publication. Zhang has also pioneered the Visual Mamba UNet, a novel segmentation architecture that fuses multi-scale attention with detail infusion, achieving state-of-the-art results in unsound corn kernel segmentation for autonomous breeding robots. Additionally, their multimodal perception system integrating vision and LiDAR enhances wheeled robot navigation accuracy. With a growing citation impact and a focus on deployable, real-world solutions, Zhang is establishing themselves as a versatile innovator at the intersection of computer vision, robotics, and sustainable agriculture.