Project AURIONAI Use-Cases Research & Innovation
geospatialfamily

Oriented object detectors for aerial images (MMRotate)

Detectors that predict rotated boxes for ships, planes, vehicles and storage tanks in aerial and satellite images, reproduced with checkpoints on DOTA in OpenMMLab MMRotate.

OpenMMLabOpenMMLabChina
OpenMMLab
Levelfamily
Classgeospatial
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

20182019202020212022RoI TransformerRoI Transformer, Dec 2018R3DetR3Det, Aug 2019Gliding VertexGliding Vertex, Nov 2019S2A-NetS2A-Net, Aug 2020ReDetReDet, Mar 2021Oriented R-CNNOriented R-CNN, Aug 2021
Northwestern Polytechnical UniversityOriented R-CNN belongs to this familygeospatial12 Aug 2021
Wuhan UniversityReDet belongs to this familygeospatial13 Mar 2021
Wuhan UniversityS2A-Net belongs to this familygeospatial21 Aug 2020
Gliding Vertex belongs to this familygeospatial21 Nov 2019
Shanghai Jiao Tong UniversityR3Det belongs to this familygeospatial15 Aug 2019
Wuhan UniversityRoI Transformer belongs to this familygeospatial1 Dec 2018
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

Industry Use Cases

Public Sector
Satellite monitoring (land cover, floods, forests)

R&D Topics

Oriented object detection in aerial imageryproduced by

Identity

Developer
OpenMMLab
Family
not in the notes
Released
– sources
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
CNN
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Also in MMRotate: Rotated RetinaNet, Rotated Faster R-CNN, Rotated FCOS, Rotated RepPoints, Rotated ATSS, CFA, Oriented RepPoints (arXiv 2105.11111), SASM, G-Rep; losses CSL, GWD, KLD and KFIoU.
Context length
not in the notes
Input
image
Output
labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Sources

  1. github.com/open-mmlab/mmrotate https://github.com/open-mmlab/mmrotate
  2. github.com/open-mmlab/mmrotate/tree/main/configs/rotated... https://github.com/open-mmlab/mmrotate/tree/main/configs/rotated_retinanet
  3. arxiv.org/abs/1708.02002 https://arxiv.org/abs/1708.02002
  4. github.com/open-mmlab/mmrotate/tree/main/configs/rotated... https://github.com/open-mmlab/mmrotate/tree/main/configs/rotated_faster_rcnn
  5. arxiv.org/abs/1506.01497 https://arxiv.org/abs/1506.01497
  6. github.com/open-mmlab/mmrotate/tree/main/configs/rotated... https://github.com/open-mmlab/mmrotate/tree/main/configs/rotated_reppoints
  7. arxiv.org/abs/1904.11490 https://arxiv.org/abs/1904.11490

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Oriented Object Detectors for Aerial Images (MMRotate)", https://aurion.semai.id/models/oriented-object-detectors/, records of October 2026.