A Semisupervised Siamese Network for Efficient Change Detection in Heterogeneous Remote Sensing Images

Abstract

Change detection in heterogeneous remote sensing images is crucial for emergencies, such as disaster assessment. Existing methods based on homogeneous transformation suffer from the high computational cost that makes the change detection tasks time-consuming. To solve this problem, this article presents a new semisupervised Siamese network (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N) based on transfer learning. In the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N, the low- and deep-level features are separated and treated differently for transfer learning. By incorporating two identical subnetworks that are both pretrained on natural images, the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N eliminates the computational cost for learning the low-level features that are universal for both remote sensing images and natural images. As the deep-level features contain different semantics between remote sensing images and natural images, a novel transfer learning strategy is presented to train only the weights of the layers for deep-level features in the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N. The decrease in the number of network parameters to be trained reduces the demand for training samples, leading to a significant decrease in computational cost. Afterward, the thresholding method, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Otsu</i> , is applied to the difference map derived by the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N to obtain the final binary map of change detection. Three data sets including different types of heterogeneous remote sensing images are employed to evaluate the performance of the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N. The experimental results demonstrate that the proposed S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N can achieve a comparable detection performance with much lower computational cost, compared with state-of-the-art change detection algorithms.