A window frame structure extraction method and system based on image segmentation and multi-image fusion

CN121811267BActive Publication Date: 2026-06-12SHENZHEN UNIV
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN UNIV
Filing Date
2026-03-12
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

In existing technologies, window frame structure extraction suffers from insufficient precision, geometric distortion, and detection errors, which severely restricts the application value of window models in LOD3 architectural 3D models.

Method used

The method employs image segmentation and multi-image fusion, which includes preprocessing the orthophoto of the building facade windows, segmenting the window frames and generating masks. By combining image segmentation and multi-image fusion algorithms, the geometric and color parameters of the window frames are extracted, and the target window frame structure is finally generated.

Benefits of technology

It enables accurate extraction of window frame structure, improving the accuracy and reliability of window models in LOD3 architectural 3D models.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121811267B_ABST
    Figure CN121811267B_ABST
Patent Text Reader

Abstract

The application belongs to the technical field of computer vision, and discloses a window frame structure extraction method and system based on image segmentation and multi-image fusion, which comprises the following steps: obtaining an orthographic window image of a building facade, and performing first preprocessing on the orthographic window image; wherein the first preprocessing comprises window clustering grouping and super-resolution processing; performing window frame segmentation on the first preprocessed orthographic window image based on an image segmentation algorithm to obtain a segmented window frame mask; fusing the window frame masks of the same cluster based on a multi-image fusion algorithm to generate a window frame fusion mask; extracting the geometric parameters and color parameters of the window frame fusion mask; and obtaining a target window frame structure according to the extracted geometric parameters and color parameters; through the steps of the image segmentation algorithm, the multi-image fusion algorithm, the geometric parameter and color parameter extraction, etc., the window frame structure corresponding to the orthographic window image can be accurately extracted.
Need to check novelty before this filing date? Find Prior Art