Complex tubes with flanges, joints and other components, characterized by a large number, diverse shapes and complex structures, are key parts of aircraft engines, rockets and other quipment. In order to ensure the smooth operation of these equipment, the dimensional accuracy of the tube is must be ensured.

A research team from the Shenyang Institute of Automation (SIA) of the Chinese Academy of Sciences has developed a novel online measurement method based on multi-camera vision and regional pre-segmentation. This new approach enables real-time, high-precision inspection of the spatial dimensions of flanged and jointed tubes.

Published in the Journal of Manufacturing Processes, the the study introduces a segmentation model powered by Triple Detail Feature Capture Fusion (TDC). This model effectively integrates multi-scale visual features, allowing the system to emphasize key structural areas—such as flanges and joints—for precise segmentation.

To quantify the flange geometry, the researchers proposed an edge-based measurement algorithm focused on the upper surface of the flange. By analyzing curvature changes and applying 3D reconstruction, they achieved accurate parameter extraction. For the tube body region, which often features linear yet fragmented structures, the researchers reconstructed the central axis to determine key spatial measurements.

Experimental results show the system can complete full tube measurement in just seven seconds, with a flange parameter accuracy of 0.17 mm and a tube body parameter accuracy of 0.16 mm—meeting the stringent demands of aerospace manufacturing.

Overall flowchart of online measurement method for complex pipelines based on area pre-segmentation (Image by SIA)