煤矿供电线路地质灾害监测中光学影像与雷达影像的像素级特征融合识别方法
By using a dual-branch heterogeneous feature adaptive token fusion method, the problems of insufficient fusion depth and lack of heterogeneous feature synergy mechanism in the geological disaster monitoring of coal mine power supply lines were solved. This method achieves high-precision and high-definition identification of geological disaster hazards and reduces the false alarm rate.
CN122157001BActive Publication Date: 2026-07-17GUIZHOU COAL MINE DESIGN & RES INST +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUIZHOU COAL MINE DESIGN & RES INST
- Filing Date
- 2026-05-09
- Publication Date
- 2026-07-17
Smart Images
Figure CN122157001B_ABST
Abstract
本发明涉及遥感影像处理、地质灾害识别与深度学习交叉技术领域，公开煤矿供电线路地质灾害监测中光学影像与雷达影像的像素级特征融合识别方法，包括：S1：获取空间匹配的光学遥感影像与多时相SAR遥感影像，形成光学‑SAR影像对；S2：将光学‑SAR影像对分别输入光学纹理特征提取分支和雷达形变特征提取分支并生成光学全局令牌与SAR全局令牌；S3：利用光学全局令牌与SAR全局令牌分别对另一分支提取的特征进行引导，并将引导结果进行自适应融合，生成融合全局令牌；S4：将融合全局令牌反向注入解码器，输出地质灾害隐患识别结果；S5：模型训练与优化。本发明提升了采空塌陷、滑坡等地质灾害隐患的识别精度与边界清晰度。
Need to check novelty before this filing date? Find Prior Art