Iron tower corrosion detection and quantitative evaluation method and system based on multi-modal fusion

By employing a multimodal fusion method for detecting corrosion in iron towers, utilizing an improved version of YOLO-World and a depth polarization camera, combined with multi-index scoring, the method addresses the issues of insufficient generalization ability and high false detection rate in existing corrosion detection technologies, achieving efficient and accurate corrosion detection and assessment.

CN122193237APending Publication Date: 2026-06-12XIAMEN FOUR FAITH COMM TECH

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIAMEN FOUR FAITH COMM TECH
Filing Date
2026-05-14
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

Existing tower corrosion detection technologies rely on a large amount of labeled data, have insufficient generalization ability, high false detection rate, cannot effectively distinguish between corrosion and defects that are similar in appearance, have a single quantitative evaluation dimension, and limited edge computing capabilities.

Method used

A multimodal fusion method is adopted, and an improved version of YOLO-World is used for preliminary identification. Depth and polarization features are obtained by combining depth and polarization cameras. The corrosion level is evaluated by weighted scoring of multiple indicators, and a progressive on-demand acquisition mechanism is adopted to reduce the amount of computation.

🎯Benefits of technology

It significantly improves the accuracy of rust detection, reduces the false detection rate, achieves scientific rust degree classification, and completes detection and evaluation independently at the edge, reducing data acquisition and computing costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122193237A_ABST
    Figure CN122193237A_ABST
Patent Text Reader

Abstract

The method and system for tower corrosion detection and quantitative evaluation based on multi-modal fusion relate to the technical field of tower corrosion detection. The method comprises the following steps: collecting an RGB image of the tower, and using a zero-shot detection model for preliminary identification to obtain a rust candidate region bounding box; performing pixel-level segmentation on the candidate region corresponding to the rust candidate region bounding box to obtain a rust region mask; after obtaining the rust region mask, obtaining a depth map and a polarization map that are accurately aligned with the RGB image by collecting data on the region corresponding to the rust region mask through a depth camera and a polarization camera; within the region defined by the rust region mask, calculating a depth feature according to the depth map and a polarization feature according to the polarization map; discriminating the rust candidate region according to the depth feature and the polarization feature, and when in a fuzzy interval, comprehensively judging in combination with a visual feature; and performing multi-index weighted scoring on the region determined as true rust to obtain a rust grade and a corresponding processing suggestion.
Need to check novelty before this filing date? Find Prior Art