缆索结构的缺陷检测方法、装置、设备及存储介质
By stitching and tiling multiple consecutive images of the cable structure and combining them with multi-scale feature detection, the problem of inaccurate detection of multi-twist defects in cables in existing technologies has been solved, and higher-precision defect identification has been achieved.
CN122048949BActive Publication Date: 2026-07-17LEVI INTELLIGENT (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- LEVI INTELLIGENT (SHENZHEN) CO LTD
- Filing Date
- 2026-04-17
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies can only detect defects in a single twist pitch of a cable, and cannot effectively identify defects in multiple twist pitches, resulting in poor detection results.
Method used
By acquiring multiple consecutive images of the cable, the feature information of the overlapping areas is used to stitch them together. Combined with the globally optimized transformation matrix and centerline extraction, a tiled image is generated. A multi-scale feature detection model is then applied to detect multi-twist defects.
Benefits of technology
It enables multi-twist defect detection in cable structures, improving the accuracy and precision of detection and allowing for earlier identification of potential fault risks.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122048949B_ABST
Abstract
本申请公开了一种缆索结构的缺陷检测方法、装置、设备及存储介质，方法包括：采集缆索结构的多张图像，多张图像包括部分重叠区域；根据重叠区域内的特征信息对图像进行拼接，得到拼接图像；基于拼接图像中缆索结构的中心线对拼接图像进行几何变换，得到平铺展开图像；对平铺展开图像进行检测，得到多捻距缺陷检测结果。本申请可以实现对各缆索的多捻距缺陷检测，提高了后续对缆索结构的故障的预测精度。
Need to check novelty before this filing date? Find Prior Art