Region-Local Copula Evidence Fusion for Heterogeneous Remote Sensing Change Detection

2026-09-26

AI Summary

This study addresses the localization accuracy limitations in heterogeneous remote sensing change detection caused by the single-label constraint of mixed superpixels. To overcome this, a regional-local Copula evidence fusion method is proposed. By preserving the regional decision structure, the approach introduces spatial local dependency to model anomalous features and fuses continuous regional confidence with local model characteristics. Furthermore, a region-dependent threshold is derived, revealing the equivalence conditions between gating mechanisms and reparameterization, while upper-tail gating combined with reference ranking strategies is employed to optimize decision-making. Experimental results demonstrate that the proposed method achieves Kappa coefficients of 0.7814 and 0.9082 on the Lake and UK datasets, respectively, significantly improving change detection accuracy within mixed regions and along boundaries.

Abstract

Superpixel copula models provide stable regional evidence for heterogeneous remote sensing change detection, but a single label per region limits localization within mixed superpixels. This letter develops a region-local copula evidence fusion method that retains the regional decision structure while introducing spatially varying local dependence anomalies. Independently fitted local models characterize departures from unchanged cross-image relationships. Reference ranking and an upper-tail gate transform these anomalies for fusion with continuous regional confidence. We derive the resulting regiondependent local decision threshold and identify a condition under which gating is equivalent to reparameterizing ungated fusion. On Lake and UK, whole-image optimized configurations achieve kappa coefficients of 0.78136 and 0.90817 and improve mixedregion and boundary decisions. Four-fold retrospective spatial validation over ten training subsets confirms complementary local information, with ungated reference fusion increasing mean kappa by 0.00693 and 0.01793. Fixed gating yields a larger UK gain of 0.03353 but only 0.00041 on Lake. These results support regional-local dependence interaction, while showing that calibration and gating have scene-dependent benefits.

Problem

• heterogeneous remote sensing
• change detection
• superpixel copula
• mixed superpixels
• localization

Innovation

• Copula evidence fusion
• Heterogeneous remote sensing
• Change detection
• Superpixel
• Local dependence anomalies