Xiaodan Wang

Air Force Engineering University, Wuhan University of Technology

Papers

Total Citations

134

H-Index

About

Xiaodan Wang is a researcher working at the intersection of computer vision, deep learning, and robotics, with a particular focus on applying intelligent algorithms to practical automation challenges. Wang's most recognized contribution is a 2019 study on fruit image classification using MobileNetV2 with transfer learning, which has garnered 132 citations and addressed a critical need in agricultural robotics. By leveraging deep convolutional neural networks, the work demonstrated how transfer learning techniques could enable accurate and efficient fruit recognition — a capability essential for robotic picking systems that reduce labor costs and enhance the global competitiveness of fruit producers. Beyond agricultural applications, Wang has also contributed to mobile robotics through improvements to the ORB-SLAM algorithm, tackling persistent challenges in simultaneous localization and mapping, including matching errors, processing speed, and positioning accuracy, by incorporating depth information derived from saliency detection. Together, these works reflect Wang's commitment to bridging advanced machine learning methodologies with real-world robotic systems. With research spanning both precision agriculture and autonomous navigation, Wang represents an emerging voice in applied AI and intelligent robotics.