ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 10. Vol. 28. 2022

DOI: 10.17587/it.28.539-545

V. A. Abramov, Master, Far Eastern Federal University, Vladivostok, Russian Federation, A. P. Kudryashov, Researcher, Institute of Automation of Control Processes FEB RAS, Vladivostok, Russian Federation

Visual Method of Pipeline Detection by an Autonomous Underwater Vehicle using a Stereo Camera

This paper describes a method for searching and recognizing extended underwater communication using a stereo camera mounted on an autonomous uninhabited underwater vehicle (AUV). The output data is a list of coordinates in three-dimensional space. The method uses a pair of stereo images as input data. The method uses stereo images to create a dense depth map and a map of height differences, with the help of which extended structures are detected. The problem of filtering the interference present on the seabed is also solved by screening out objects whose size does not correspond to the expected size of the pipeline. The algorithm calculates the coordinates of the selected point on a two-dimensional image and projects it into three-dimensional space. Thus, the algorithm gets the coordinates of the point through which the pipeline build. The objectives of the work are: description of the method, setting up an experiment on a virtual model, description of the experiment and its results. The paper presents a step-by-step method for solving the problem, presents the results of an experiment set on a virtual model. The algorithm confidently determined the selected pipe in clean areas, and areas with interference having a height greater than the pipeline. As a result, a list of coordinates is obtained through which the virtual pipeline runs. Further development and improvement of the developed method is possible
Keywords: stereo camera, AUV, pipeline, recognition, depth map, object identification, images, object detection, contour detection

P. 539–545

To the contents