The Development of Underwater Inspection Technique Applying Image Detection Mode

  • 黃 琳晉

Student thesis: Master's Thesis


In this thesis the authors describe the development of an image detection mode to support the optimal route plan of Autonomous Underwater Vehicle (AUV) when inspecting offshore wind farms The program LABVIEW is used to simulate the AUV’s trajectory In addition a modular structure is applied to program design in this study The structure is composed of a fuzzy controller module 6DOF motion module an image detection module and a dynamic routing module In terms of path planning the optimal route is selected using the Multi-Objective Particle Swarm algorithm (MOPSO) method and virtual images of obstacles Thus each feasible route is searched iteratively according to two objectives namely sailing time and energy consumption In the image virtualization process acquired points are distributed over a limited space and environmental depths for identifying the features of obstacles are visualized using stereo vision In summary the system is not only beneficial for optimizing feasible routes but it can also identify features of obstacles for the purpose of positioning Eventually several underwater objects such as wind turbine foundations cables and obstacles would be incorporated into and tested in the simulation for combining image detection with underwater AUV inspection
Date of Award2016 Aug 18
Original languageEnglish
SupervisorYu-Hsien Lin (Supervisor)

Cite this