Changjie Qin

Papers

Total Citations

H-Index

About

Changjie Qin is a researcher advancing the frontiers of underwater computer vision and marine technology. Their primary research areas encompass deep learning-based object detection, particularly for challenging underwater environments, and the development of efficient neural network architectures for real-time applications. Qin’s most notable contribution is the MSD-YOLOv5 algorithm, a specialized adaptation of the YOLOv5 framework designed to overcome the unique difficulties of underwater biological target detection—such as light attenuation, low contrast, and complex backgrounds. This work, published in 2023, demonstrates how multi-scale feature extraction can significantly improve the accuracy and speed of identifying aquatic organisms, with direct applications in autonomous underwater robotics, marine surveillance, and precision aquaculture. By enabling robots to better detect seabed features, identify vessels and swimmers, and help farmers monitor species distribution and stocking densities, Qin’s research bridges the gap between theoretical computer vision and practical oceanographic needs. Though early in its citation impact, this work represents a meaningful step toward more intelligent, automated marine monitoring systems that can support both ecological research and sustainable industry practices.