DDL R-CNN: Dynamic Direction Learning R-CNN for Rotated Object Detection
Current remote sensing (RS) detectors often rely on predefined anchor boxes with fixed angles to handle the multi-directional variations of targets. This approach makes it challenging to accurately select regions of interest and extract features that align with the direction of the targets. Most exi...
Saved in:
Main Authors: | Weixian Su, Donglin Jing |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2025-01-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/18/1/21 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Oriented R-CNN With Disentangled Representations for Product Packaging Detection
by: Jiangyi Pan, et al.
Published: (2024-01-01) -
FAMHE-Net: Multi-Scale Feature Augmentation and Mixture of Heterogeneous Experts for Oriented Object Detection
by: Yixin Chen, et al.
Published: (2025-01-01) -
Fast Object Detection and Localization in Ultrawide Swath Rotating Scan Remote Sensing Images
by: Zhiming Deng, et al.
Published: (2025-01-01) -
Advancing Wildlife Protection: Mask R-CNN for Rail Track Identification and Unwanted Object Detection
by: Istiak Mahmud, et al.
Published: (2023-01-01) -
Inclined Aerial Image and Satellite Image Matching Based on Edge Curve Direction Angle Features
by: Hao Wang, et al.
Published: (2025-01-01)