Home

Awesome

Oriented RepPoints for Aerial Object Detection

Wentong Li, Yijie Chen, Kaixuan Hu, Jianke Zhu* (Arxiv)

<img src="https://github.com/LiWentomng/OrientedRepPoints/blob/main/docs/overallnetwork.png" width="800px">

Update

Installation

Please refer to install.md for installation and dataset preparation.

Getting Started

This repo is based on mmdetection. Please see getting_started.md for the basic usage.

Results and Models

The results on DOTA test set are shown in the table below. More detailed results please see the paper.

ModelBackbonedata aug(HSV+Rotation)mAPmodellog
OrientedReppointsR-5075.97modellog
OrientedReppointsR-10176.52modellog
OrientedReppointsSwin-Tiny78.11modellog

Note:

The mAOE results on DOTA val set are shown in the table below.

ModelBackbonemAOEDownload
OrientedReppointsR-505.93°model

Note:Orientation error evaluation (mAOE) is calculated on the val subset(only train subset for training).

Visual results

The visualization code for oriented bounding boxes and learning points is here.

<img src="https://github.com/LiWentomng/OrientedRepPoints/blob/main/docs/visualization.png" width="800px">

Citation

@inproceeding{orientedreppoints,
	title="Oriented RepPoints for Aerial Object Detection.",
	author="Wentong {Li}, Yijie {Chen}, Kaixuan {Hu}, Jianke {Zhu}.",
	journal="The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",
	year="2022"
}

Acknowledgements

Here are some great resources we benefit. We would espeicially thank the authors of:

MMdetection

RepPoints

AerialDetection

BeyondBoundingBox