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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In recent years, building change detection methods have made great progressby introducing deep learning, but they still suffer from the problem of theextracted features not being discriminative enough, resulting in incompleteregions and irregular boundaries. To tackle this problem, we propose a dualtask constrained deep Siamese convolutional network (DTCDSCN) model, whichcontains three sub-networks: a change detection network and two semanticsegmentation networks. DTCDSCN can accomplish both change detection andsemantic segmentation at the same time, which can help to learn morediscriminative object-level features and obtain a complete change detectionmap. Furthermore, we introduce a dual attention module (DAM) to exploit theinterdependencies between channels and spatial positions, which improves thefeature representation. We also improve the focal loss function to suppress thesample imbalance problem. The experimental results obtained with the WHUbuilding dataset show that the proposed method is effective for building changedetection and achieves a state-of-the-art performance in terms of four metrics:precision, recall, F1-score, and intersection over union.

Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model