A Mobile Platform for AI-Powered Underwater Image Processing
Chenyu Zhou, Lily Walker, Xin Fu, Jiefu Chen, Yueqin Huang, Xuqing Wu · Offshore Technology Conference · 2025
Abstract Timely inspection of subsea infrastructure, particularly pipelines, is crucial for preventing oil spills and protecting the environment. This paper introduces a groundbreaking technology for offshore pipeline inspection, centered on an autonomous robotic system equipped with underwater computer vision and edge computing capabilities. The aim is to create a fast and cost-effective solution for inspecting underwater structures, enabling the early detection of environmental hazards and avoiding catastrophic outcomes. In this paper, we focus on the workflow for deploying a pre-trained deep neural network (DNN) model onto an autonomous underwater vehicle equipped with video cameras and mobile edge computing devices. The DNN is specifically trained for various underwater image and video processing tasks. By using this intelligent computer vision system, the autonomous underwater vehicle can navigate and track objects even in low-visibility conditions. This efficient and affordable approach ensures that pipeline leaks and ruptures can be detected early, empowering operators to take timely action and reduce environmental risks.