Feixiang Zhou
Papers
2
Total Citations
21
H-Index
2
About
Feixiang Zhou is a leading researcher in underwater computer vision, specializing in object detection and image enhancement for challenging aquatic environments. His work directly addresses the critical limitations of deep learning models in real-world underwater settings, where poor visibility, color distortion, and low contrast degrade performance. Zhou’s most impactful contribution is SWIPENET, a novel object detection framework designed to robustly handle noisy underwater imagery, which has garnered 14 citations since its 2020 publication. He further advanced the field by introducing a benchmark dataset that simultaneously supports both underwater image enhancement and object detection—a pioneering dual-purpose resource cited 7 times. This dataset is instrumental for developing and evaluating preprocessing techniques that boost high-level vision tasks. Zhou’s research is vital for applications in marine engineering and autonomous aquatic robotics, bridging the gap between controlled laboratory conditions and the unpredictable underwater world. His work not only improves detection accuracy but also provides standardized tools for the research community, making him a key figure in advancing reliable vision systems for underwater exploration and monitoring.
Research Focus
Key Achievements
Top Papers
- 1SWIPENET: Object detection in noisy underwater images14 citations · 2020
- 2