Development of a Robotic System with Stand-Alone Monocular Vision System for Eco-friendly Defect Detection in Oil Transportation Pipelines

Abstract

This paper presents development of a pipeline defect detection (PDD) system and designing main components of the system to reduce the risk of environmental pollution due to pipeline accidents. Main feature presented is a robotic system including a pipe navigation mechanism and a vision system. ExPIRo robot platform developed at the previous stage of the research is used as the moving mechanism for the robotic system with minor modifications. Vision system is developed by the integration of a camera module, a single board computer and a remote workstation. PDD system presented provides remote monitoring and analyzing features by utilizing the remote workstation for data storage. MATLAB-based image acquisition algorithm is performed on LATTEPANDA single board computer, whereas the defect identification algorithm is performed on HP Envy 6-1012TX Ultra-Book laptop. GUI developed for the system visualizes the stages of image analysis and displays result while updating the result of each image for defect identification purpose. External surface defects having significant appearance abnormalities are tested using the presented PDD system, images of pipe segments are captured, and defects are successfully identified.