Abstract
This paper presents a multiscale feature-guided residual convolutional neural network (ResCNN) method for synthetic aperture radar (SAR) image change detection. The proposed method uses four convolutional kernels of different sizes to extract multi-scale features and fuses the features to make the representation more powerful. In addition, the proposed method introduces three residual blocks to form a CNN with more than ten layers. The deep network with residuals can ensure that the model can extract robust high-level semantic features from the image and avoid the gradient dispersion problem in backpropagation. The proposed method uses pseudo labels to guide network training, which is unsupervised. Visualize and quantify results for the real SAR data sets show that the depth network and multi-scale features help improve the model's change detection performance.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
