English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With the rapid development of deep learning, a variety of change detectionmethods based on deep learning have emerged in recent years. However, thesemethods usually require a large number of training samples to train the networkmodel, so it is very expensive. In this paper, we introduce a completelyunsupervised shallow convolutional neural network (USCNN) fusion approach forchange detection. Firstly, the bi-temporal images are transformed intodifferent feature spaces by using convolution kernels of different sizes toextract multi-scale information of the images. Secondly, the output features ofbi-temporal images at the same convolution kernels are subtracted to obtain thecorresponding difference images, and the difference feature images at the samescale are fused into one feature image by using 1 * 1 convolution layer.Finally, the output features of different scales are concatenated and a 1 * 1convolution layer is used to fuse the multi-scale information of the image. Themodel parameters are obtained by a redesigned sparse function. Our model hasthree features: the entire training process is conducted in an unsupervisedmanner, the network architecture is shallow, and the objective function issparse. Thus, it can be seen as a kind of lightweight network model.Experimental results on four real remote sensing datasets indicate thefeasibility and effectiveness of the proposed approach.

Unsupervised convolutional neural network fusion approach for change detection in remote sensing images