Chenggang Dai

Qingdao University of Science and Technology

Papers

Total Citations

H-Index

About

Chenggang Dai is a rising researcher in the field of computer vision and underwater robotics, with a primary focus on efficient deep learning models for object detection in challenging environments. His most-cited work introduces a novel one-stage multi-scale efficient network built upon YOLOv5s, specifically designed to overcome the persistent challenges of low precision on small and densely packed underwater targets. By addressing the complexities of murky, low-visibility aquatic settings, Dai’s method significantly enhances detection accuracy and speed, offering a practical solution for autonomous underwater vehicles and marine monitoring systems. With 6 citations to date, this foundational paper is already gaining traction among peers working on real-time detection in degraded visual conditions. Dai’s contributions are notable for bridging the gap between lightweight neural architectures and robust performance in non-ideal environments, making his work highly relevant for applications in ocean exploration, environmental surveillance, and underwater search operations. As an emerging voice in efficient vision systems, Chenggang Dai is poised to make further impacts in adaptive, resource-constrained detection technologies.