Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss

Arbitrary-oriented objects exist widely in remote sensing images. The mainstream rotation detectors use oriented bounding boxes (OBBs) or quadrilateral bounding boxes (QBBs) to represent the rotating objects. However, these methods suffer from the representation ambiguity for oriented object definit...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5
Hauptverfasser:	Ming, Qi, Miao, Lingjuan, Zhou, Zhiqiang, Yang, Xue, Dong, Yunpeng
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Bounding box regression Boxes convolutional neural networks Detectors Invariance Localization Matching Minima Object detection Object recognition Optimization oriented object detection Quadrilaterals Regression Remote sensing representation ambiguity Representations Rotation Task analysis Training Transforms
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!