A landslide change detection sample enhancement method considering terrain factors

By mosaicking landslide patches onto slope areas under the guidance of topographic factors, landslide change detection samples with obvious visual and morphological differences are generated, which solves the problem of sample scarcity in landslide change detection and enables full training and regional transfer applications of complex models.

CN121010850BActive Publication Date: 2026-04-21CHINA AERO GEOPHYSICAL SURVEY & REMOTE SENSING CENT FOR LAND & RESOURCES
2 Cites 0 Cited by

Patent Information

Application Number
CN202511118875.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-08-11
Publication Date
2026-04-21
Estimated Expiration
2045-08-11

AI Technical Summary

Technical Problem

Existing technologies lack large-scale labeled samples in landslide change detection, making it difficult to train cutting-edge intelligent models. Furthermore, existing sample augmentation methods generate samples with insufficient feature differences, affecting model training effectiveness and prediction performance.

Method used

By mosaicking landslide patches onto slope areas that differ significantly from them, and combining topographical factors such as slope and aspect, landslide change detection samples with obvious visual and morphological differences are generated, ensuring the rationality of the spatial location of the samples.

Benefits of technology

It can quickly generate a large number of landslide change detection samples with obvious visual and morphological differences, solving the problems of difficult model training and poor regional transferability under small sample conditions, and promoting the application and improvement of cutting-edge artificial intelligence models in landslide change detection tasks.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This invention provides a landslide change detection sample enhancement method considering topographic factors, belonging to the field of image processing technology. The method includes: cropping landslide samples to obtain pixel clusters with the ground truth label "landslide" as landslide mask samples, and performing random X and Y axis flipping and / or random angle rotation; selecting scene samples without landslide labels, calculating the normalized mutual information between the post-landslide image corresponding to the landslide mask sample and the post-temporal image of the scene sample, obtaining candidate scenes and calculating the slope aspect and slope of each pixel to obtain slope areas prone to landslide development; obtaining mosaic candidate areas in the slope areas prone to landslide development, calculating the average slope aspect, determining the slope aspect, and mosaicking the transformed landslide mask sample onto the mosaic candidate area to obtain a new landslide change detection sample. This invention rapidly generates landslide change detection samples by mosaicking landslide patches onto slope areas with significant differences, ensuring reasonableness.
Need to check novelty before this filing date? Find Prior Art