Two-Layer Slow Feature Analysis Network for Change Detection

Abstract

Multi-temporal remote sensing image change detection is one of the important contents of remote sensing image processing, and has important applications in many fields. Existing multi-temporal change detection mainly deals with bi-temporal images and extracts change information by ratio or difference method. This processing cannot effectively mine the change information between multiple temporal images or time series of remote sensing images. In this paper, a two-layer slow feature analysis network (SFANet) is proposed to realize effective change detection with multiple temporal remote sensing images. The proposed method extends the existing slow feature analysis method to a two-layer network structure and forms a slow feature analysis network. On the basis of multi-temporal feature extraction in slow feature analysis network, change detection is realized by threshold method. In this paper, multi-temporal high-resolution remote sensing images are used for experiments. The experimental results demonstrate that the proposed SFANet for change detection is effective and better than several commonly used methods.