Coupled dictionary learning for unsupervised change detection between multimodal remote sensing images

• Published in: Computer vision and image understanding Vol. 189; pp. 102817 - 15
• Main Authors: Ferraris, Vinicius, Dobigeon, Nicolas, Cavalcanti, Yanna, Oberlin, Thomas, Chabert, Marie
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.12.2019; Elsevier
• Subjects: Change detection; Computer Science; Computer Vision and Pattern Recognition; Coupled dictionary learning; Multimodality; Optical images; SAR image; Change detection; Multimodality; Optical images; Coupled dictionary learning; SAR image
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2019.102817

Archetypal scenarios for change detection generally consider two images acquired through sensors of the same modality. However, in some specific cases such as emergency situations, the only images available may be those acquired through sensors of different modalities. This paper addresses the problem of unsupervisedly detecting changes between two observed images acquired by sensors of different modalities with possibly different resolutions. These sensor dissimilarities introduce additional issues in the context of operational change detection that are not addressed by most of the classical methods. This paper introduces a novel framework to effectively exploit the available information by modeling the two observed images as a sparse linear combination of atoms belonging to a pair of coupled overcomplete dictionaries learnt from each observed image. As they cover the same geographical location, codes are expected to be globally similar, except for possible changes in sparse spatial locations. Thus, the change detection task is envisioned through a dual code estimation which enforces spatial sparsity in the difference between the estimated codes associated with each image. This problem is formulated as an inverse problem which is iteratively solved using an efficient proximal alternating minimization algorithm accounting for nonsmooth and nonconvex functions. The proposed method is applied to real images with simulated yet realistic and real changes. A comparison with state-of-the-art change detection methods evidences the accuracy of the proposed strategy. •Multimodal change detection is formulated as a coupled dictionary learning problem.•The method is able to handle multimodal images with possibly different resolution.•Coupled dictionary learning and codes estimated using alternating optimization.•Algorithmic solution for nonconvex problem with convergence to critical point.•The performance is assessed on a comprehensive set of experiments.