MidNet: An Anchor-and-Angle-Free Detector for Oriented Ship Detection in Aerial Images
- 30 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-13
Abstract
Ship detection in aerial images remains an active yet challenging task due to its arbitrary object orientation and various aspect ratios from the bird’s-eye perspective. Most existing oriented objection detection methods rely on angular prediction or predefined anchor boxes, making these methods highly sensitive to unstable angular regression and excessive hyper-parameter setting. To address these issues, we replace the angular-based object encoding with an anchor-and-angle-free paradigm, and propose a novel detector deploying a center and four midpoints for encoding each oriented object, namely MidNet. Moreover, MidNet designs a novel symmetrical deformable convolution for enhanceing the features of midpoints, then the center and midpoints for an identical ship are adaptively matched by predicting corresponding centripetal shift and matching radius. Finally, a concise analytical geometry algorithm is proposed to calculate the ship orientation and refine the keypoints step-wisely for building precise oriented bounding boxes. On two public ship detection datasets, HRSC2016 and FGSD2021, MidNet outperforms the state-of-the-art detectors by achieving APs of 90.52% and 86.50%.Keywords
Funding Information
- National Natural Science Foundation of China (62271374, 62176200, 62077038, 62176196)
- State Key Program of National Natural Science of China (61836009)
- Natural Science Basic Research Program of Shaanxi (2022GY-065, 2022JC-45)
- Fundamental Research Funds for the Central Universities (QTZX23047)
This publication has 36 references indexed in Scilit:
- CornerNet: Detecting Objects as Paired Keypoints2018
- R2CNN: Rotational Region CNN for Arbitrarily-Oriented Scene Text Detection2018
- Arbitrary-Oriented Scene Text Detection via Rotation ProposalsIEEE Transactions on Multimedia, 2018
- Focal Loss for Dense Object Detection2017
- Deformable Convolutional Networks2017
- Rotated region based CNN for ship detection2017
- Aggregated Residual Transformations for Deep Neural Networks2017
- A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines2017
- Deep Residual Learning for Image Recognition2016
- Microsoft COCO: Common Objects in Context2014