Method and system for positioning drill rod of trenchless drilling machine based on image segmentation

By constructing a drill pipe panoramic image segmentation network model and deep learning technology, the accuracy of drill pipe positioning in complex backgrounds is solved, efficient and reliable drill pipe identification and positioning is achieved, and the accuracy of coordinate system calibration is ensured.

CN119693461AActive Publication Date: 2025-03-25JIANGNAN UNIV +1
8 Cites 1 Cited by

Patent Information

Application Number
CN202510206761.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-25
Publication Date
2025-03-25
Estimated Expiration
2045-02-25

AI Technical Summary

Technical Problem

The prior art is difficult to accurately detect the position and attitude of the drill rod of the non-excavation drill rig in complex contexts, and cannot ensure the accuracy of the coordinate system calibration.

Method used

Using an image segmentation method, the drill pipe panoramic image segmentation network model is constructed, and the drill pipe is automatically segmented from the panoramic image using deep learning technology, edge features are extracted, the furthest point pair and the minimum area rectangle are calculated, and the position information of the drill pipe is obtained, and the positioning accuracy is ensured through the conversion of camera coordinates to world coordinates.

Benefits of technology

It realizes accurate detection of the position and attitude of the drill pipe in a complex context, ensures the accuracy of coordinate system calibration, improves the efficiency and reliability of drill pipe identification, and reduces the need for manual operation.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a positioning method and system for a drill rod of a trenchless drilling machine based on image segmentation, and belongs to the technical field of image segmentation. Comprising the following steps: constructing a drill rod panoramic image segmentation network model, and training the drill rod panoramic image segmentation network model by using an image data set to obtain an optimized image segmentation network model; obtaining a drill rod panoramic image of a to-be-positioned drill rod, and inputting the drill rod panoramic image into the optimized image segmentation network model to generate a segmentation result image; edge features of the segmentation result image are extracted, and an edge coordinate point set of the to-be-positioned drill rod is obtained; calculating the edge coordinate point set to obtain a farthest point pair; calculating the distance between the farthest point pair to obtain a minimum area rectangle; and acquiring a center coordinate of the minimum-area rectangle, converting the center coordinate into a camera coordinate, then converting the camera coordinate into a world coordinate, and obtaining position information of the to-be-positioned drill rod. The position and posture of the drill rod can be accurately detected under the complex background, and the accuracy of coordinate system calibration is ensured.
Need to check novelty before this filing date? Find Prior Art