GAN-Based Siamese Framework for Landslide Inventory Mapping Using Bi-Temporal Optical Remote Sensing Images

Regarding landslide inventory mapping (LIM) as a task similar to change detection, current methods for LIM using bi-temporal optical remote sensing images are generally derived from change detection methods. In practice, not all changed regions belong to landslides, e.g., new roads, canals, and vegetation. Therefore, an ideal strategy is supposed to present two steps: discriminating changed and unchanged regions, and detecting landslides apart from other changed regions. Owing to the complexity and uncertainty of landslides, it is difficult to simultaneously separate landslides with unchanged and other changed regions by a single model. Addressing this problem, in this letter, we apply a generative adversarial network (GAN) in a Siamese neural network, and then propose a GAN-based Siamese framework (GSF) for LIM. The GSF comprises two cascaded modules, namely, domain adaptation and landslide detection. The former module aims to make a cross-domain mapping between prelandslide and postlandslide images with adversarial learning, then translate paired images into the same domain to suppress the domain discrepancies of bi-temporal remote sensing images. Meanwhile, the latter module aims to perform pixel-level landslide detection with a Siamese model. By training this cascaded framework, our method learns to produce landslide inventory maps without any preprocessing or postprocessing. Extensive experiments and comparison with other state-of-the-art methods verify the efficiency and superiority of our method.

Automated summary

This letter proposes a new framework for landslide inventory mapping, using a combination of generative adversarial network and Siamese neural network, with two cascaded modules for domain adaptation and landslide detection. The method is proven to efficiently and accurately produce landslide inventory maps from bi-temporal remote sensing images.