Seismic landslide detection method and device combining coherence increase and vegetation damage

By combining the fusion technology of post-seismic coherence increase and vegetation damage data, the problem of low accuracy of existing landslide detection methods is solved, and more accurate landslide area identification and reliability of detection results is achieved, providing effective data support for earthquake landslide disaster assessment.

CN119689466AActive Publication Date: 2025-03-25YUNNAN NORMAL UNIV
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202510207728.X
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 existing landslide detection methods rely on single coherent change information and are susceptible to natural environment changes and noise interference, resulting in mis-checking or missed detection, affecting the accuracy and reliability of the detection results.

Method used

The seismic landslide detection method with joint coherence increase and vegetation damage is adopted. By acquiring post-seismic coherence data and vegetation damage data, data fusion is used to generate fusion images, and landslide area identification is performed through mask processing and segmentation technology.

Benefits of technology

It improves the accuracy and reliability of earthquake landslide detection, can identify landslide areas more comprehensively and accurately, provide clear and intuitive landslide spatial distribution information, and provides reliable data support for post-earthquake landslide disaster assessment and emergency response.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119689466A_ABST
    Figure CN119689466A_ABST
Patent Text Reader

Abstract

The invention discloses an earthquake landslide detection method and device combining coherence increase and vegetation damage. The method comprises the following steps: determining a coherence graph when an earthquake occurs and after the earthquake according to earthquake coherence data; comparing the coherence graph when the earthquake occurs with the coherence graph after the earthquake, and generating a coherence increase graph after the earthquake; based on the dual-polarized radar vegetation index, quantifying vegetation damage conditions in the to-be-detected target area before and after the earthquake, and generating a post-earthquake vegetation damage map; the post-earthquake coherence increase graph and the post-earthquake vegetation damage graph are fused through wavelet transform; the fusion image is segmented into a landslide area and a non-landslide area, a fusion image after segmentation processing is obtained, a mask file is determined based on satellite optical data, mask processing is carried out on the fusion image after segmentation processing by using the mask file, and seismic landslide detection is carried out on a to-be-detected target area based on the fusion image after mask processing. According to the invention, the landslide area can be comprehensively and accurately identified, and the precision of earthquake landslide detection is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Landslide detection method, device and equipment and storage medium

    CN114694030A

  • Landslide identification method based on SAR image, storage medium and processor

    CN115424146A

  • Earthquake area landslide identification and susceptibility evaluation method

    CN118196642A

  • Landslide disaster early recognition method considering interference baseline optimization

    CN118230258A

  • Landslide disaster identification and extraction method, system and equipment based on GEE-SAR (Geographic Evolution-Synthetic Aperture Radar)

    CN118968319A