MidNet: An Anchor-and-Angle-Free Detector for Oriented Ship Detection in Aerial Images

TL;DR

MidNet introduces an anchor-and-angle-free method for oriented ship detection in aerial images, improving accuracy and robustness by replacing angular prediction with a midpoint-based encoding and geometric refinement.

Contribution

The paper proposes a novel anchor-and-angle-free detector, MidNet, utilizing midpoints and a geometric algorithm for precise oriented ship detection, overcoming limitations of existing angular-based methods.

Findings

Achieves 90.52% AP on HRSC2016 dataset.

Outperforms state-of-the-art detectors in ship detection accuracy.

Demonstrates competitive results on DOTA dataset.

Abstract

Ship detection in aerial images remains an active yet challenging task due to arbitrary object orientation and complex background from a bird's-eye perspective. Most of the existing 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. MidNet designs a symmetrical deformable convolution customized for enhancing the midpoints of ships, 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 refine the centers and midpoints 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%. Additionally, MidNet obtains competitive results in the ship detection of DOTA.