Shengxian Wang

Papers

Total Citations

H-Index

About

Shengxian Wang’s research focuses on agricultural robotics and computer vision, with a particular emphasis on improving object detection and pose estimation for real-world applications. His major contributions include developing lightweight deep learning methods for fruit detection in natural environments, as demonstrated in his most-cited paper, “Tomato detection in natural environment based on improved YOLOv8 network” (2025, 2 citations). This work addresses critical challenges in precision agriculture—such as subtle ripeness differences and occlusion by branches—by enhancing the YOLOv8 backbone to achieve efficient, accurate tomato ripeness classification. Wang also contributed to assistive robotics with “Pose estimation of daily containers for a life-support robot” (2018, 2 citations), which tackles 3D pose estimation for household objects to aid robotic manipulation. Though his citation counts are early-stage, his work bridges practical agricultural needs with advanced neural network architectures, offering scalable solutions for automated harvesting and robotic assistance. Wang’s research is particularly relevant for students and engineers interested in deploying computer vision in unstructured environments, where robustness and computational efficiency are paramount. His ongoing work promises to impact smart farming and service robotics.