Yetong Shang

Papers

Total Citations

H-Index

About

Yetong Shang is a researcher whose work sits at the intersection of marine robotics and computer vision, with a focused interest in underwater object detection for automated harvesting. Their most-cited paper, "Underwater Sea Cucumber Identification Based on Improved YOLOv5" (2022, 28 citations), addresses a critical bottleneck in developing autonomous underwater collection robots. Shang proposed a novel enhancement to the YOLOv5 architecture specifically tailored for the challenging underwater environment, enabling accurate real-time identification and localization of sea cucumbers. This contribution is significant not only for aquaculture automation but also for advancing machine vision in low-visibility, high-noise aquatic settings. By tackling a niche yet economically important problem, Shang’s work demonstrates how deep learning can be adapted for specialized marine tasks. The paper’s citation count reflects its practical value to researchers and engineers working on underwater robotics and precision aquaculture. Shang’s research exemplifies the growing trend of applying state-of-the-art AI techniques to solve real-world environmental and agricultural challenges, making their work a valuable reference for students and professionals interested in the convergence of marine biology, robotics, and computer vision.