Qingshuang Hu

Papers

Total Citations

132

H-Index

About

Qingshuang Hu is a researcher at the forefront of applying deep learning to agricultural automation, with a particular focus on fruit image classification for robotic harvesting. Her most influential work, "Fruit Image Classification Based on MobileNetV2 with Transfer Learning Technique" (2019), has garnered over 130 citations, reflecting its significant impact on the field. In this study, Hu pioneered the use of MobileNetV2—a lightweight deep convolutional neural network—combined with transfer learning to achieve highly accurate and efficient fruit recognition. This approach directly addresses the critical challenge of enabling robots to identify and pick fruit in real-world orchard environments, promising to reduce labor costs and enhance global competitiveness for fruit producers. By optimizing deep learning models for edge devices, Hu's contributions bridge the gap between state-of-the-art computer vision and practical agricultural robotics. Her work not only advances the technical frontier of precision agriculture but also offers scalable solutions for the food supply chain, making her a key figure in the growing intersection of AI and sustainable farming.