A Semisupervised Siamese Network for Efficient Change Detection in Heterogeneous Remote Sensing Images
- 9 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892), 1-18
- https://doi.org/10.1109/tgrs.2021.3061686
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 3 N) based on transfer learning. In the proposed S 3 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 3 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 3 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, Otsu , is applied to the difference map derived by the proposed S 3 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 3 N. The experimental results demonstrate that the proposed S 3 N can achieve a comparable detection performance with much lower computational cost, compared with state-of-the-art change detection algorithms.Keywords
Funding Information
- National Natural Science Foundation of China (61790551, 61925106)
- Civil Space Advance Research Program of China (D010305)
This publication has 43 references indexed in Scilit:
- SAR Images Change Detection Based on Spatial Coding and Nonlocal Similarity PoolingIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?IEEE Transactions on Medical Imaging, 2016
- Going deeper with convolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Standard Plane Localization in Fetal Ultrasound via Domain Transferred Deep Neural NetworksIEEE Journal of Biomedical and Health Informatics, 2015
- A New Multivariate Statistical Model for Change Detection in Images Acquired by Homogeneous and Heterogeneous SensorsIEEE Transactions on Image Processing, 2014
- Learning and Transferring Mid-level Image Representations Using Convolutional Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Object-based land cover change detection for cross-sensor imagesInternational Journal of Remote Sensing, 2013
- Supervised change detection in VHR images using contextual information and support vector machinesInternational Journal of Applied Earth Observation and Geoinformation, 2013
- Monitoring Land-Use Change in Nakuru (Kenya) Using Multi-Sensor Satellite DataAdvances in Remote Sensing, 2012
- Satellite radar and optical remote sensing for earthquake damage detection: results from different case studiesInternational Journal of Remote Sensing, 2006