Building deformation detection method and device, electronic equipment and storage medium

By constructing a local coherence network in building inspection and selecting the optimal reference point, the atmospheric error problem caused by the selection of reference benchmark in traditional methods is solved, and high-precision detection and evaluation of differential deformation inside buildings is achieved.

CN121898285BActive Publication Date: 2026-06-19SHENZHEN URBAN PUBLIC SAFETY & TECH INST CO LTD +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN URBAN PUBLIC SAFETY & TECH INST CO LTD
Filing Date
2026-03-20
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Traditional time-series InSAR processing methods have limitations in reference selection when monitoring individual buildings, leading to atmospheric errors and affecting the accuracy of detecting differential deformations such as uneven settlement and thermal expansion within the building.

Method used

By extracting the vector frame of the target building in the geographic coordinate system and projecting it onto the SAR image coordinate system, a candidate set of stable points is screened, a local coherence network is constructed, the optimal reference point is selected, the deformation time series is calculated, and local relative deformation detection is performed.

Benefits of technology

It improves the accuracy of detecting differential deformation inside buildings, reduces atmospheric errors, is suitable for analyzing differential deformations such as uneven settlement and torsion, and provides a refined structural health assessment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121898285B_ABST
    Figure CN121898285B_ABST
Patent Text Reader

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for detecting building deformation. The method involves extracting a first vector frame of the target building in a geographic coordinate system, projecting this first vector frame onto a SAR image coordinate system to obtain a second vector frame in the SAR image coordinate system, extracting a subset of interferometric phase data for each pixel within the second vector frame, and selecting a candidate set of stable points from this subset. A local coherence network is constructed based on the candidate set of stable points, and an optimal reference point is selected from the local coherence network. The deformation time series of other reference points within the local coherence network relative to the optimal reference point is calculated, and the deformation detection result of the target building is determined based on the deformation time series. This invention selects the optimal reference point within the local network of each building, forming a local relative deformation detection network for that building, which is more suitable for analyzing differential deformations such as uneven settlement and torsion within buildings.
Need to check novelty before this filing date? Find Prior Art