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

Oriented object detection in aerial images is a challenging task as theobjects in aerial images are displayed in arbitrary directions and are usuallydensely packed. Current oriented object detection methods mainly rely ontwo-stage anchor-based detectors. However, the anchor-based detectors typicallysuffer from a severe imbalance issue between the positive and negative anchorboxes. To address this issue, in this work we extend the horizontalkeypoint-based object detector to the oriented object detection task. Inparticular, we first detect the center keypoints of the objects, based on whichwe then regress the box boundary-aware vectors (BBAVectors) to capture theoriented bounding boxes. The box boundary-aware vectors are distributed in thefour quadrants of a Cartesian coordinate system for all arbitrarily orientedobjects. To relieve the difficulty of learning the vectors in the corner cases,we further classify the oriented bounding boxes into horizontal and rotationalbounding boxes. In the experiment, we show that learning the box boundary-awarevectors is superior to directly predicting the width, height, and angle of anoriented bounding box, as adopted in the baseline method. Besides, the proposedmethod competes favorably with state-of-the-art methods. Code is available athttps://github.com/yijingru/BBAVectors-Oriented-Object-Detection.

Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors