Region-local copula models improve mixed region remote sensing change detection
Region-Local Copula Evidence Fusion for Heterogeneous Remote Sensing Change Detection
Computer Vision and Pattern Recognition
Summary
Detecting changes in satellite or aerial images can be tricky when different land types mix in one area. The authors developed a new approach that looks both at larger regions and at smaller local differences to better spot changes. Their method uses statistical models to identify unusual local patterns while still considering the overall region. Tests showed it improves accuracy, especially near boundaries and mixed areas, and works differently depending on the scene.
What this means in practice
- •For remote sensing analysts: Detect land cover changes more precisely in mixed or boundary regions by combining regional and local image evidence with copula models.
- •For geospatial data engineers: Integrate spatially localized anomaly detection to refine change maps produced from heterogeneous satellite images for better decision-support products.
Authors
Zhiyuan Ji, Junjun Yin, Jian Yang
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.