Slow Feature Analysis for Change Detection in Multispectral Imagery

• Published in: IEEE transactions on geoscience and remote sensing Vol. 52; no. 5; pp. 2858 - 2874
• Main Authors: Wu, Chen, Du, Bo, Zhang, Liangpei
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied geophysics; Change detection; Change detection algorithms; Covariance matrices; Detection algorithms; Earth sciences; Earth, ocean, space; Eigenvalues and eigenfunctions; Exact sciences and technology; Feature extraction; Image detection; image transformation; Internal geophysics; Invariants; Pixels; Principal component analysis; Remote sensing; slow feature analysis (SFA); Spectra; Spectral bands; image transformation; Change detection; slow feature analysis (SFA); experimental studies; algorithms; Thematic Mapper; imagery; transformations; remote sensing; technology; Pixel
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2013.2266673

Change detection was one of the earliest and is also one of the most important applications of remote sensing technology. For multispectral images, an effective solution for the change detection problem is to exploit all the available spectral bands to detect the spectral changes. However, in practice, the temporal spectral variance makes it difficult to separate changes and nonchanges. In this paper, we propose a novel slow feature analysis (SFA) algorithm for change detection. Compared with changed pixels, the unchanged ones should be spectrally invariant and varying slowly across the multitemporal images. SFA extracts the most temporally invariant component from the multitemporal images to transform the data into a new feature space. In this feature space, the differences in the unchanged pixels are suppressed so that the changed pixels can be better separated. Three SFA change detection approaches, comprising unsupervised SFA, supervised SFA, and iterative SFA, are constructed. Experiments on two groups of real Enhanced Thematic Mapper data sets show that our proposed method performs better in detecting changes than the other state-of-the-art change detection methods.