Fenglei Han

Papers

Total Citations

250

H-Index

About

Fenglei Han is a researcher whose work sits at the intersection of computer vision, deep learning, and underwater robotics — fields with growing significance in the exploration and sustainable use of marine environments. Han's research focuses primarily on applying deep convolutional neural network (CNN) methods to the unique challenges posed by underwater imaging, including poor visibility, high pressure, and low-light conditions that make traditional image processing techniques unreliable. Among Han's most impactful contributions is a 2020 study on underwater image processing and object detection using deep CNN methods, which has garnered 171 citations, reflecting its substantial influence on the field of autonomous underwater systems. This work addresses the critical need for intelligent computer vision in deep-sea autonomous operations, reducing human exposure to dangerous high-pressure environments. A complementary 2020 paper on marine organism detection and classification — earning 79 citations — demonstrates Han's applied focus, targeting the automation of seafloor harvesting tasks such as collecting sea cucumbers, sea urchins, and scallops. Together, these contributions position Han as a meaningful voice in advancing safe, intelligent underwater robotics and marine resource utilization through cutting-edge machine learning techniques.