GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Sign in
  • ActionsCI/CD and automation
  • CodespacesCloud development environments
  • All Features
  • Documentation
  • Training
  • Certifications
  • Build with Copilot
  • Customize Copilot
  • Integrations
  • Trending repos
  • GitHub Sponsors
  • Developer articles
  • Enterprises

This view

  • Original page
  • New address

GeezerVison is showing github.com — GitHub - ming71/TIOE: [ISPRS&RS 2023]Official implementation of "Task Interleaving and Orientation Estimation for High-Precision Oriented Object Detection in Aerial Images".

BranchesTags
Open more actions menu

Latest commit

 

History

6 Commits
6 Commits

Folders and files

NameName
Last commit message
Last commit date
DOTA_devkit
DOTA_devkit
 
 
config
config
 
 
docs
docs
 
 
models
models
 
 
tools
tools
 
 
utils
utils
 
 
LICENSE
LICENSE
 
 
README.md
README.md
 
 
compile.sh
compile.sh
 
 
demo.sh
demo.sh
 
 
hubconf.py
hubconf.py
 
 
prepare.sh
prepare.sh
 
 
requirements.txt
requirements.txt
 
 
test.sh
test.sh
 
 
train.sh
train.sh
 
 

Repository files navigation

TIOE-Det

This project hosts the official implementation for the paper:

Task Interleaving and Orientation Estimation for High-Precision Oriented Object Detection in Aerial Images [URL][PDF][BibTex]

( accepted by ISPRS Journal of Photogrammetry and Remote Sensing).

Abstract

In this paper, we propose a Task Interleaving and Orientation Estimation Detector for high-quality oriented object detection in aerial images. Specifically, a posterior hierarchical alignment (PHA) indicator is proposed to optimize the detection pipeline. TIOE-Det adopts PHA indicator to integrate fine-grained posterior localization guidance into classification task to address the misalignment between classification and localization subtasks. Then, a balanced alignment loss is developed to solve the imbalance localization loss contribution in PHA prediction. Moreover, we propose a progressive orientation estimation (POE) strategy to approximate the orientation of objects with n-ary codes. On this basis, an angular deviation weighting strategy is proposed to achieve accurate evaluation of angle deviation in POE strategy.

Framework

framework

Setup

conda create -n tioe python=3.6 -y
source activate tioe
pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html

sudo apt-get install swig
pip install -r requirements.txt

cd  DOTA_devkit
swig -c++ -python polyiou.i
python setup.py build_ext --inplace
cd ..

sh compile.sh

Training

  • Creat config files.
  • Dataset transformation via running sh prepare.sh.
  • Run sh train.sh.

Inference & Testing

  • Run sh demo.sh and sh test.sh.

Visualizations

demo

Citation

If you find our work or code useful in your research, please consider citing:

@article{MING2023241,
title={Task interleaving and orientation estimation for high-precision oriented object detection in aerial images},
author={Qi Ming and Lingjuan Miao and Zhiqiang Zhou and Junjie Song and Yunpeng Dong and Xue Yang},
journal={ISPRS Journal of Photogrammetry and Remote Sensing},
volume={196},
pages={241-255},
year={2023},
issn = {0924-2716},
doi = {https://doi.org/10.1016/j.isprsjprs.2023.01.001},
}

Feel free to contact me if there are any questions.

About

[ISPRS&RS 2023]Official implementation of "Task Interleaving and Orientation Estimation for High-Precision Oriented Object Detection in Aerial Images".

Resources

Readme
Apache-2.0 license
Activity

Stars

31 stars

Watchers

0 watching

Forks

1 fork
Report repository

Releases

Packages

Used by

Contributors

Languages

You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.