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

Detecting oriented objects along with estimating their rotation informationis one crucial step for analyzing remote sensing images. Despite that manymethods proposed recently have achieved remarkable performance, most of themdirectly learn to predict object directions under the supervision of only one(e.g. the rotation angle) or a few (e.g. several coordinates) groundtruthvalues individually. Oriented object detection would be more accurate androbust if extra constraints, with respect to proposal and rotation informationregression, are adopted for joint supervision during training. To this end, weinnovatively propose a mechanism that simultaneously learns the regression ofhorizontal proposals, oriented proposals, and rotation angles of objects in aconsistent manner, via naive geometric computing, as one additional steadyconstraint (see Figure 1). An oriented center prior guided label assignmentstrategy is proposed for further enhancing the quality of proposals, yieldingbetter performance. Extensive experiments demonstrate the model equipped withour idea significantly outperforms the baseline by a large margin to achieve anew state-of-the-art result without any extra computational burden duringinference. Our proposed idea is simple and intuitive that can be readilyimplemented. Source codes and trained models are involved in supplementaryfiles.

Learning Oriented Remote Sensing Object Detection via Naive Geometric Computing