Change Detection Based on Deep Features and Low Rank

• Published in: IEEE geoscience and remote sensing letters Vol. 14; no. 12; pp. 2418 - 2422
• Main Authors: Hou, Bin, Wang, Yunhong, Liu, Qingjie
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Change detection; Change detection (CD); convolutional neural network (CNN); Earth; Feasibility studies; Feature extraction; Image detection; Image segmentation; low rank; Matrix decomposition; Methods; Multilevel; Neural networks; Remote sensing; remote sensing (RS); Salience; Sparse matrices; visual saliency; Visualization
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2017.2766840

In this letter, we address the problem of change detection for remote sensing images from the perspective of visual saliency computation. The proposed method incorporates low-rank-based saliency computation and deep feature representation. First, multilevel convolutional neural network (CNN) features are extracted for superpixels generated using SLIC, in which a fixed-size CNN feature can be formed to represent each superpixel. Then, low-rank decomposition is applied to the change features of the two input images to generate saliency maps that indicate change probabilities of each pixel. Finally, binarized change map can be obtained with a simple threshold. To deal with scale variations, a multiscale fusion strategy is employed to produce more reliable detection results. Extensive experiments on Google Earth and GF-2 images demonstrate the feasibility and effectiveness of the proposed method.