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

In synthetic aperture radar (SAR) image change detection, it is quitechallenging to exploit the changing information from the noisy difference imagesubject to the speckle. In this paper, we propose a multi-scale spatial pooling(MSSP) network to exploit the changed information from the noisy differenceimage. Being different from the traditional convolutional network with onlymono-scale pooling kernels, in the proposed method, multi-scale pooling kernelsare equipped in a convolutional network to exploit the spatial contextinformation on changed regions from the difference image. Furthermore, toverify the generalization of the proposed method, we apply our proposed methodto the cross-dataset bitemporal SAR image change detection, where the MSSPnetwork (MSSP-Net) is trained on a dataset and then applied to an unknowntesting dataset. We compare the proposed method with other state-of-arts andthe comparisons are performed on four challenging datasets of bitemporal SARimages. Experimental results demonstrate that our proposed method obtainscomparable results with S-PCA-Net on YR-A and YR-B dataset and outperformsother state-of-art methods, especially on the Sendai-A and Sendai-B datasetswith more complex scenes. More important, MSSP-Net is more efficient thanS-PCA-Net and convolutional neural networks (CNN) with less executing time inboth training and testing phases.

A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images