Data

Tools

Indexes

Applications

Experiments

Open Source Science

skylinedet-yolov11seg

This code is published for skyline detection

https://github.com/kuazhangxiaoai/skylinedet-yolov11seg

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.2%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

This code is published for skyline detection

Basic Info
  • Host: GitHub
  • Owner: kuazhangxiaoai
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 4.05 MB
Statistics
  • Stars: 8
  • Watchers: 1
  • Forks: 1
  • Open Issues: 4
  • Releases: 0
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

YUNet: Imprived YOLOv11 Network for Skyline Detection

DeepSeek-V3

Abstract

Skyline detection plays an important role in unmanned aerial vehicle (UAV) control systems. The appearance of the sky and non-sky areas are variable, because of different weather or illumination environment, which brings challenges to skyline detection. In this research, we proposed the YUNet algorithm, which combined the YOLOv11 and Unet architecture to extract the skyline in complicated and variable circumstances. To improve the ability of multi-scale and large range contextual feature fusion of Unet, the YOLOv11 architecture is extended as an UNet-like architecture, consisting of a encoder, decoder and neck submodule. The encoder submodule extracts the features from the given images, while the decoder submodule leverages the features from neck submodule to compelete the prediction rebuilding. The neck submodule can make fusion of the multiscale and large range contextual features. To validate the approach in this research, it was tested on two public datasets including Skyfinder and CH1 datasets.

Dataset

There are two expriments about this code, which are sky segmentation and skyline detection. The sky segmentation is run on skyfinder dataset. For the skyline detection, the train process is run on geopose3k dataset, and the validation is run on CH1 dataset. The three datasets is preprocessed and pubulished at following. 1. Skyfinder: Baidu Drive 2. geoPose3k: Baidu Drive 3. CH1: Baidu Drive

Configuration

We add the global configuration file skyseg.yaml into the directory of ultralytics/cfg. Users can revise the train, validation, and test configuration at ultralytics/cfg/skyseg.yaml

We add the dataset configuration file skyfinder.yaml and geoPose3k.yaml into the directory of ultralytics/cfg/datasets. User can set the path of dataset at ultralytics/cfg/datasets/skyfinder.yaml and ultralytics/cfg/datasets/geoPose3k.yaml

Train

The entrance of train process is writen into ultralytics/model/yolo/skyseg/train.py. After complete the configuration file, Users can train the model by the following command. shell python train.py

Validation

The entrance of validation process is writen into ultralytics/model/yolo/skyseg/val.py. After complete the configuration file, Users can validate the model by the following command. shell python val.py

Model

| Benchmark | Accuracy | Precision | Recall | Dice-Score | IoU | Size | BaiduDrive | GoogleDrive | |-----------|----------|-----------|--------|------------|--------|------|------------------|----------------------------------------------------------------------------------------------------| | YOLOv11-n | 99.195 | 98.308 | 98.834 | 98.513 | 0.9719 | 7.2MB | **[Download](https://pan.baidu.com/s/1JUHHQchwc9Iect3tJycrgA?pwd=wsuj)** | **[Download](https://drive.google.com/file/d/1RCDWtzL5_ERvy87739BLttqtjtvtdcw5/view?usp=sharing)** | | | YOLOv11-s | 99.467 | 99.169 | 98.969 | 99.042 | 0.9816 | 24.8MB | **[Download](https://pan.baidu.com/s/1yZV2C6E_wxwkpKjWYtt3Pg?pwd=ijwh)** | **[Download](https://drive.google.com/file/d/1wQefjuXMKrQLT-FZ2opcwXy5FOYc07vz/view?usp=sharing)** | | YOLOv11-m | 99.479 | 99.382 | 98.809 | 99.078 | 0.9821 | 51.4MB | **[Download](https://pan.baidu.com/s/1VsBZmojjjyp5agSnIZ7hxQ?pwd=c7hh)** | **[Download](https://drive.google.com/file/d/1QXPhs1KWEiD_Ze0QyLLXEtHf5ghd0z2G/view?usp=sharing)** | | | YOLOv11-l | 99.406 | 99.186 | 99.034 | 99.036 | 0.9824 | 65.3MB | **[Download](https://pan.baidu.com/s/1_ZsF2VAtuL075ZXlHfXsKg?pwd=wu1p)** | **[Download](https://drive.google.com/file/d/1HbZxLND7ojvegxyL_DKpp5NSIr6_ScWf/view?usp=sharing)** | | | YOLOv11-x | 99.565 | 99.465 | 99.101 | 99.253 | 0.9858 | 145.8MB | **[Download](https://pan.baidu.com/s/1nEDZQcy6FVKWGCnClok5Jg?pwd=r93m)** | **[Download](https://drive.google.com/file/d/11FdmWxOKi0qHi_s8OZFkj4LF99UoB3GG/view?usp=sharing)** |

Citation

@misc{yang2025yunetimprovedyolov11network,
      title={YUNet: Improved YOLOv11 Network for Skyline Detection}, 
      author={Gang Yang and Miao Wang and Quan Zhou and Jiangchuan Li},
      year={2025},
      eprint={2502.12449},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2502.12449}, 
}

Owner

  • Name: yanggang
  • Login: kuazhangxiaoai
  • Kind: user
  • Location: Beijing
  • Company: BISM

Citation (CITATION.cff) 

# This CITATION.cff file was generated with https://bit.ly/cffinit

cff-version: 1.2.0
title: Ultralytics YOLO
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Glenn
    family-names: Jocher
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0001-5950-6979'
  - family-names: Qiu
    given-names: Jing
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0003-3783-7069'
  - given-names: Ayush
    family-names: Chaurasia
    affiliation: Ultralytics
    orcid: 'https://orcid.org/0000-0002-7603-6750'
repository-code: 'https://github.com/ultralytics/ultralytics'
url: 'https://ultralytics.com'
license: AGPL-3.0
version: 8.0.0
date-released: '2023-01-10'

GitHub Events

Total
  • Issues event: 4
  • Watch event: 9
  • Delete event: 3
  • Issue comment event: 22
  • Push event: 1
  • Pull request event: 9
  • Fork event: 2
  • Create event: 8
Last Year
  • Issues event: 4
  • Watch event: 9
  • Delete event: 3
  • Issue comment event: 22
  • Push event: 1
  • Pull request event: 9
  • Fork event: 2
  • Create event: 8

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 3
  • Total pull requests: 6
  • Average time to close issues: about 21 hours
  • Average time to close pull requests: about 2 months
  • Total issue authors: 3
  • Total pull request authors: 1
  • Average comments per issue: 1.0
  • Average comments per pull request: 2.17
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 6
Past Year
  • Issues: 3
  • Pull requests: 6
  • Average time to close issues: about 21 hours
  • Average time to close pull requests: about 2 months
  • Issue authors: 3
  • Pull request authors: 1
  • Average comments per issue: 1.0
  • Average comments per pull request: 2.17
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 6
View more stats
Top Authors
Issue Authors
  • NielsRogge (1)
  • Mediumcore (1)
  • Jordan-Pierce (1)
Pull Request Authors
  • dependabot[bot] (5)
Top Labels
Issue Labels
question (2)
Pull Request Labels

Dependencies

.github/workflows/ci.yaml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • codecov/codecov-action v4 composite
  • conda-incubator/setup-miniconda v3 composite
  • slackapi/slack-github-action v1.27.0 composite
.github/workflows/cla.yml actions
  • contributor-assistant/github-action v2.6.1 composite
.github/workflows/codeql.yaml actions
  • actions/checkout v4 composite
  • github/codeql-action/analyze v3 composite
  • github/codeql-action/init v3 composite
.github/workflows/docs.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
.github/workflows/format.yml actions
  • ultralytics/actions main composite
.github/workflows/links.yml actions
  • actions/checkout v4 composite
  • nick-invision/retry v3 composite
.github/workflows/merge-main-into-prs.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
.github/workflows/publish.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • pypa/gh-action-pypi-publish release/v1 composite
  • slackapi/slack-github-action v1.27.0 composite
.github/workflows/stale.yml actions
  • actions/stale v9 composite
examples/YOLO-Series-ONNXRuntime-Rust/Cargo.toml cargo
examples/YOLOv8-ONNXRuntime-Rust/Cargo.toml cargo
docker/Dockerfile docker
  • pytorch/pytorch 2.5.0-cuda12.4-cudnn9-runtime build
pyproject.toml pypi
  • matplotlib >=3.3.0
  • numpy <2.0.0; sys_platform == 'darwin'
  • numpy >=1.23.0
  • opencv-python >=4.6.0
  • pandas >=1.1.4
  • pillow >=7.1.2
  • psutil *
  • py-cpuinfo *
  • pyyaml >=5.3.1
  • requests >=2.23.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • torch >=1.8.0
  • torch >=1.8.0,!=2.4.0; sys_platform == 'win32'
  • torchvision >=0.9.0
  • tqdm >=4.64.0
  • ultralytics-thop >=2.0.0
.github/workflows/docker.yaml actions
  • actions/checkout v4 composite
  • docker/login-action v3 composite
  • docker/setup-buildx-action v3 composite
  • docker/setup-qemu-action v3 composite
  • nick-invision/retry v3 composite
  • slackapi/slack-github-action v1.27.0 composite
  • ultralytics/actions/cleanup-disk main composite