Feature-level fusion of landsat-8 oli-swir and tirs images for fine burned area change detection

This paper proposes a novel feature-level fusion approach for fire area change detection at a fine level. Two features, including a normalized burn ratio-SWIR (NBRSWIR) fire index based on Landsat-8 OLI SWIR data and the brightness temperature (BT) based on Landsat-8 TIRS data, are combined by using the gradient transfer fusion (GTF) algorithm and a change detection technique to generate a fine fire change map. A real Landsat-8 data set covering a complex fire disaster scenario was utilized to test the performance of the proposed approach. Experimental results demonstrated the effectiveness of the proposed feature-level fusion approach comparing with the reference methods in term of higher separability value and detection accuracy.