Abstract
AbstractUnderwater oil pipeline inspection is an important field in the application of underwater robot. In the experimental environment, different shapes of attachments are used to represent different oil leakage points. Different shapes of oil leakage points are identified by underwater robots, and alarms are given by acousto-optic signals. In this paper, a semi open frame KAPI underwater robot is used. The robot realizes visual recognition and motion control of pipeline inspection based on Raspberry Pi and STM32. In image preprocessing, the binary processing of the collected image is used to avoid the interference of ambient light and shadow on the circle and square, the denoising, smoothing and transformation are carried out before pattern recognition. And, the image is denoised by the erosion-dilation algorithm. The number of sides of the shape of the pipe attachment is obtained by polygon fitting based on Douglas-Pucker algorithm to judge the shape of the attachment. The feasibility of the method based on machine vision is verified by experiments.KeywordsMachine visionUnderwater robotPipeline inspectionPolygon fittingKAPI
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
