12 October 2017 Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network
Author Affiliations +
J. of Applied Remote Sensing, 11(4), 042615 (2017). doi:10.1117/1.JRS.11.042615
Abstract
This paper proposes a model of dual-channel convolutional neural network (CNN) that is designed for change detection in SAR images, in an effort to acquire higher detection accuracy and lower misclassification rate. This network model contains two parallel CNN channels, which can extract deep features from two multitemporal SAR images. For comparison and validation, the proposed method is tested along with other change detection algorithms on both simulated SAR images and real-world SAR images captured by different sensors. The experimental results demonstrate that the presented method outperforms the state-of-the-art techniques by a considerable margin.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Tao Liu, Ying Li, Ying Cao, Qiang Shen, "Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network," Journal of Applied Remote Sensing 11(4), 042615 (12 October 2017). https://doi.org/10.1117/1.JRS.11.042615 Submission: Received 31 March 2017; Accepted 22 September 2017
Submission: Received 31 March 2017; Accepted 22 September 2017
JOURNAL ARTICLE
13 PAGES


SHARE
RELATED CONTENT

Parallel algorithms for high-speed SAR processing
Proceedings of SPIE (November 20 1998)
SiSAR: advanced SAR simulation
Proceedings of SPIE (November 21 1995)

Back to Top