์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

DOTA8 ๋ฐ์ดํ„ฐ ์„ธํŠธ

์†Œ๊ฐœ

Ultralytics DOTA8์€ ์ž‘์ง€๋งŒ ๋‹ค์–‘ํ•œ ์šฉ๋„๋กœ ํ™œ์šฉ ๊ฐ€๋Šฅํ•œ ๋ฌผ์ฒด ๊ฐ์ง€ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋กœ, ๋ถ„ํ• ๋œ DOTAv1 ์„ธํŠธ์˜ ์ฒซ 8๊ฐœ ์ด๋ฏธ์ง€ ์ค‘ ํ›ˆ๋ จ์šฉ ์ด๋ฏธ์ง€ 4๊ฐœ์™€ ๊ฒ€์ฆ์šฉ ์ด๋ฏธ์ง€ 4๊ฐœ๋กœ ๊ตฌ์„ฑ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋ฌผ์ฒด ๊ฐ์ง€ ๋ชจ๋ธ์„ ํ…Œ์ŠคํŠธํ•˜๊ณ  ๋””๋ฒ„๊น…ํ•˜๊ฑฐ๋‚˜ ์ƒˆ๋กœ์šด ๊ฐ์ง€ ์ ‘๊ทผ ๋ฐฉ์‹์„ ์‹คํ—˜ํ•˜๋Š” ๋ฐ ์ด์ƒ์ ์ž…๋‹ˆ๋‹ค. 8๊ฐœ ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋˜์–ด ์žˆ์–ด ๊ด€๋ฆฌํ•˜๊ธฐ ์‰ฌ์šฐ๋ฉด์„œ๋„ ํ›ˆ๋ จ ํŒŒ์ดํ”„๋ผ์ธ์˜ ์˜ค๋ฅ˜๋ฅผ ํ…Œ์ŠคํŠธํ•˜๊ณ  ๋” ํฐ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ํ›ˆ๋ จํ•˜๊ธฐ ์ „์— ๊ฑด์ „์„ฑ ๊ฒ€์‚ฌ ์—ญํ• ์„ ํ•  ์ˆ˜ ์žˆ์„ ๋งŒํผ ๋‹ค์–‘ํ•ฉ๋‹ˆ๋‹ค.

์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” Ultralytics HUB ๋ฐ YOLOv8.

๋ฐ์ดํ„ฐ ์„ธํŠธ YAML

๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์„ฑ์„ ์ •์˜ํ•˜๋Š” ๋ฐ๋Š” YAML(๋˜ ๋‹ค๋ฅธ ๋งˆํฌ์—… ์–ธ์–ด) ํŒŒ์ผ์ด ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค. ์—ฌ๊ธฐ์—๋Š” ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ฒฝ๋กœ, ํด๋ž˜์Šค ๋ฐ ๊ธฐํƒ€ ๊ด€๋ จ ์ •๋ณด์— ๋Œ€ํ•œ ์ •๋ณด๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. DOTA8 ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ฒฝ์šฐ, ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ dota8.yaml ํŒŒ์ผ์€ ๋‹ค์Œ ์œ„์น˜์—์„œ ์œ ์ง€๋ฉ๋‹ˆ๋‹ค. https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/dota8.yaml.

ultralytics/cfg/datasets/dota8.yaml

# Ultralytics YOLO ๐Ÿš€, AGPL-3.0 license
# DOTA8 dataset 8 images from split DOTAv1 dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
# Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
# parent
# โ”œโ”€โ”€ ultralytics
# โ””โ”€โ”€ datasets
#     โ””โ”€โ”€ dota8  โ† downloads here (1MB)

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/dota8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images

# Classes for DOTA 1.0
names:
  0: plane
  1: ship
  2: storage tank
  3: baseball diamond
  4: tennis court
  5: basketball court
  6: ground track field
  7: harbor
  8: bridge
  9: large vehicle
  10: small vehicle
  11: helicopter
  12: roundabout
  13: soccer ball field
  14: swimming pool

# Download script/URL (optional)
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/dota8.zip

์‚ฌ์šฉ๋ฒ•

์ด๋ฏธ์ง€ ํฌ๊ธฐ๊ฐ€ 640์ธ 100๊ฐœ์˜ ์—ํฌํฌ์— ๋Œ€ํ•ด DOTA8 ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ YOLOv8n-obb ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ๋‹ค์Œ ์ฝ”๋“œ ์กฐ๊ฐ์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ์ธ์ˆ˜์˜ ์ „์ฒด ๋ชฉ๋ก์€ ๋ชจ๋ธ ํ•™์Šต ํŽ˜์ด์ง€๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์—ด์ฐจ ์˜ˆ์‹œ

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n-obb.pt")  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data="dota8.yaml", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo obb train data=dota8.yaml model=yolov8n-obb.pt epochs=100 imgsz=640

์ƒ˜ํ”Œ ์ด๋ฏธ์ง€ ๋ฐ ์ฃผ์„

๋‹ค์Œ์€ DOTA8 ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ด๋ฏธ์ง€์™€ ํ•ด๋‹น ์ฃผ์„์˜ ๋ช‡ ๊ฐ€์ง€ ์˜ˆ์‹œ์ž…๋‹ˆ๋‹ค:

๋ฐ์ดํ„ฐ ์„ธํŠธ ์ƒ˜ํ”Œ ์ด๋ฏธ์ง€

  • ๋ชจ์ž์ดํฌ ์ด๋ฏธ์ง€: ์ด ์ด๋ฏธ์ง€๋Š” ๋ชจ์ž์ดํฌ๋œ ๋ฐ์ดํ„ฐ ์„ธํŠธ ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋œ ํ›ˆ๋ จ ๋ฐฐ์น˜์˜ ์˜ˆ์‹œ์ž…๋‹ˆ๋‹ค. ๋ชจ์ž์ดํฌ๋Š” ์—ฌ๋Ÿฌ ์ด๋ฏธ์ง€๋ฅผ ํ•˜๋‚˜์˜ ์ด๋ฏธ์ง€๋กœ ๊ฒฐํ•ฉํ•˜์—ฌ ๊ฐ ํ›ˆ๋ จ ๋ฐฐ์น˜ ๋‚ด์—์„œ ๋‹ค์–‘ํ•œ ๊ฐœ์ฒด์™€ ์žฅ๋ฉด์„ ๋Š˜๋ฆฌ๊ธฐ ์œ„ํ•ด ํ›ˆ๋ จ ์ค‘์— ์‚ฌ์šฉ๋˜๋Š” ๊ธฐ์ˆ ์ž…๋‹ˆ๋‹ค. ์ด๋ฅผ ํ†ตํ•ด ๋‹ค์–‘ํ•œ ๊ฐ์ฒด ํฌ๊ธฐ, ์ข…ํšก๋น„ ๋ฐ ์ปจํ…์ŠคํŠธ์— ์ผ๋ฐ˜ํ™”ํ•˜๋Š” ๋ชจ๋ธ์˜ ๋Šฅ๋ ฅ์„ ํ–ฅ์ƒ์‹œํ‚ฌ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

์ด ์˜ˆ์‹œ๋Š” DOTA8 ๋ฐ์ดํ„ฐ ์„ธํŠธ์— ํฌํ•จ๋œ ์ด๋ฏธ์ง€์˜ ๋‹ค์–‘์„ฑ๊ณผ ๋ณต์žก์„ฑ, ๊ทธ๋ฆฌ๊ณ  ํ›ˆ๋ จ ๊ณผ์ •์—์„œ ๋ชจ์ž์ดํฌ ์‚ฌ์šฉ์˜ ์ด์ ์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.

์ธ์šฉ ๋ฐ ๊ฐ์‚ฌ

์—ฐ๊ตฌ ๋˜๋Š” ๊ฐœ๋ฐœ ์ž‘์—…์— DOTA ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜๋Š” ๊ฒฝ์šฐ ๋‹ค์Œ ๋…ผ๋ฌธ์„ ์ธ์šฉํ•ด ์ฃผ์„ธ์š”:

@article{9560031,
  author={Ding, Jian and Xue, Nan and Xia, Gui-Song and Bai, Xiang and Yang, Wen and Yang, Michael and Belongie, Serge and Luo, Jiebo and Datcu, Mihai and Pelillo, Marcello and Zhang, Liangpei},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title={Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges},
  year={2021},
  volume={},
  number={},
  pages={1-1},
  doi={10.1109/TPAMI.2021.3117983}
}

์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ํ๋ ˆ์ดํŒ…ํ•˜๋Š” ๋ฐ ๋งŽ์€ ๋…ธ๋ ฅ์„ ๊ธฐ์šธ์ธ DOTA ๋ฐ์ดํ„ฐ ์„ธํŠธ ์ œ์ž‘ํŒ€์—๊ฒŒ ํŠน๋ณ„ํžˆ ๊ฐ์‚ฌ์˜ ๋ง์”€์„ ์ „ํ•ฉ๋‹ˆ๋‹ค. ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ๊ทธ ๋‰˜์•™์Šค์— ๋Œ€ํ•ด ์ž์„ธํžˆ ์•Œ์•„๋ณด๋ ค๋ฉด ๊ณต์‹ DOTA ์›น์‚ฌ์ดํŠธ๋ฅผ ๋ฐฉ๋ฌธํ•˜์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค.



Created 2024-01-09, Updated 2024-06-02
Authors: glenn-jocher (2), Laughing-q (1)

๋Œ“๊ธ€