CD-GAN: A robust fusion-based generative adversarial network for unsupervised remote sensing change detection with heterogeneous sensors

• Published in: Information fusion Vol. 107
• Main Authors: Wang, Jin-Ju, Dobigeon, Nicolas, Chabert, Marie, Wang, Ding-Cheng, Huang, Ting-Zhu, Huang, Jie
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.07.2024; Elsevier
• Subjects: Adversarial training; Change detection; Computer Science; Computer Vision and Pattern Recognition; Engineering Sciences; Fusion; Heterogeneous sensors; Image Processing; Machine Learning; Signal and Image processing; Spatial sparsity; Statistics; Adversarial training; Change detection; Fusion; Spatial sparsity; Heterogeneous sensors; fusion; heterogeneous sensors; change detection; spatial sparsity; adversarial training
• ISSN: 1566-2535; 1872-6305
• DOI: 10.1016/j.inffus.2024.102313

In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e.g., optical or radar). Even when considering only optical images, this task has proven to be challenging as soon as the sensors differ by their spatial and/or spectral resolutions. This paper proposes a novel unsupervised change detection method dedicated to images acquired by such so-called heterogeneous optical sensors. It capitalizes on recent advances which formulate the change detection task into a robust fusion framework. Adopting this formulation, the work reported in this paper shows that any off-the-shelf network trained beforehand to fuse optical images of different spatial and/or spectral resolutions can be easily complemented with a network of the same architecture and embedded into an adversarial framework to perform change detection. A comparison with state-of-the-art change detection methods demonstrates the versatility and the effectiveness of the proposed approach. •Detecting changes between images acquired by heterogeneous sensors is formulated as a robust fusion problem.•The method is able to handle multi-band images with possibly different spatial and/or spectral resolutions.•The method is unsupervised, i.e., it does not need a train set composed of image pairs with associated binary change maps.•Any pretrained deep network designed to fuse heterogeneous images can be reused to perform change detection.•When compared to conventional approaches, the strategy appears to be more flexible while competing favorably.