A Method and System for Dual-Channel Screening of InSAR Deformation Points Based on Spatiotemporal Neighborhood Features

Abstract

The present invention discloses a method and system for dual-channel screening of InSAR deformation points based on spatiotemporal neighborhood features. By constructing a 5×5 spatial window and a 7-period time-series image spatiotemporal neighborhood feature cube, the neighborhood consistency score C is calculated; using dual-channel dynamic correction, when γ < 0.3 and C > 0.9, the spatiotemporal gradient G is used for secondary verification, and if G > 10mm / month, the deformation point is retained. The 3D-CNN and Transformer are utilized to extract spatiotemporal features, adaptively optimizing to reduce false alarms of fixed thresholds, and improving the accuracy and reliability of

Images