OASL: Orientation-aware adaptive sampling learning for arbitrary oriented object detection
Arbitrary oriented object detection (AOOD) is a fundamental task in aeiral image interpretation, which is commonly implemented by optimizing three subtasks: classification, localization, and orientation. The consistency of classification, localization, and orientation is crucial for achieving high p...
Main Authors: | Zifei Zhao, Shengyang Li |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-04-01
|
Series: | International Journal of Applied Earth Observations and Geoinformation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224000943 |
Similar Items
-
FCOSR: An Anchor-free Method for Arbitrary-oriented Ship Detection in SAR Images
by: Changgui XU, et al.
Published: (2022-06-01) -
Arbitrary-Oriented Ellipse Detector for Ship Detection in Remote Sensing Images
by: Kexue Zhou, et al.
Published: (2023-01-01) -
Single-Stage Rotation-Decoupled Detector for Oriented Object
by: Bo Zhong, et al.
Published: (2020-10-01) -
One-Stage Arbitrary-Oriented Object Detection With Prediction Decoupling
by: Zhaolong Xiong
Published: (2022-01-01) -
Axis Learning for Orientated Objects Detection in Aerial Images
by: Zhifeng Xiao, et al.
Published: (2020-03-01)