Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 57; no. 12; pp. 9976 - 9992
• Main Authors: Du, Bo, Ru, Lixiang, Wu, Chen, Zhang, Liangpei
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-12-2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Analysis; Artificial neural networks; Change detection; Change detection algorithms; Components; Datasets; deep network; Detection; Detection algorithms; Eigenvalues and eigenfunctions; Feature extraction; Image detection; Imagery; Machine learning; Mapping; Methods; Remote sensing; remote sensing images; slow feature analysis (SFA); Training; Vector analysis
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2019.2930682

Change detection has been a hotspot in the remote sensing technology for a long time. With the increasing availability of multi-temporal remote sensing images, numerous change detection algorithms have been proposed. Among these methods, image transformation methods with feature extraction and mapping could effectively highlight the changed information and thus has a better change detection performance. However, the changes of multi-temporal images are usually complex, and the existing methods are not effective enough. In recent years, the deep network has shown its brilliant performance in many fields, including feature extraction and projection. Therefore, in this paper, based on the deep network and slow feature analysis (SFA) theory, we proposed a new change detection algorithm for multi-temporal remotes sensing images called deep SFA (DSFA). In the DSFA model, two symmetric deep networks are utilized for projecting the input data of bi-temporal imagery. Then, the SFA module is deployed to suppress the unchanged components and highlight the changed components of the transformed features. The change vector analysis pre-detection is employed to find unchanged pixels with high confidence as training samples. Finally, the change intensity is calculated with chi-square distance and the changes are determined by threshold algorithms. The experiments are performed on two real-world data sets and a public hyperspectral data set. The visual comparison and the quantitative evaluation have shown that DSFA could outperform the other state-of-the-art algorithms, including other SFA-based and deep learning methods.