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

Ensemble methods are a reliable way to combine several models to achievesuperior performance. However, research on the application of ensemble methodsin the remote sensing object detection scenario is mostly overlooked. Twoproblems arise. First, one unique characteristic of remote sensing objectdetection is the Oriented Bounding Boxes (OBB) of the objects and the fusion ofmultiple OBBs requires further research attention. Second, the widely used deeplearning object detectors provide a score for each detected object as anindicator of confidence, but how to use these indicators effectively in anensemble method remains a problem. Trying to address these problems, this paperproposes OBBStacking, an ensemble method that is compatible with OBBs andcombines the detection results in a learned fashion. This ensemble method helpstake 1st place in the Challenge Track \textit{Fine-grained Object Recognitionin High-Resolution Optical Images}, which was featured in \textit{2021 GaofenChallenge on Automated High-Resolution Earth Observation Image Interpretation}.The experiments on DOTA dataset and FAIR1M dataset demonstrate the improvedperformance of OBBStacking and the features of OBBStacking are analyzed.

OBBStacking: An Ensemble Method for Remote Sensing Object Detection