Matching of Corrosion Features in Multiset Pipeline In-Line Inspection Data Utilizing Relative Point Positions

Abstract Pipeline in-line inspection (ILI) stands out as an effective approach for comprehensively understanding the conditions of pipelines. Matching of corrosion features detected in multiset pipeline ILI is an essential prerequisite to determining corrosion growth. State-of-the-art methods for corrosion defect matching require the iterative process to find the optimal affine transformation or the extraction of individual defect attributes for matching model training. However, not only are these processes labor intensive, but the collection of substantial amounts of data is also challenging. To simplify the matching process, an automated method was proposed to match corrosion features that use the position of the features. This algorithm requires only the positions of detected corrosion points and applies to complex defect scenarios with high corrosion density. Firstly, triangles are constructed based on corrosion features. Secondly, local matching was employed to identify matching triangle pairs within two ILIs. Then, a global matching strategy was applied to refine the initially identified matches, filtering the false matches based on predefined requirements. Finally, the points in the final pairs of matched triangles serve as correspondences to determine the registration transformation. Experiments were conducted to validate the efficacy of the proposed method. The results demonstrate its reliability in accurately matching features within pipelines, which supports the integrity and risk assessment of pipeline systems.