์ฝ˜ํ…์ธ ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ

์ฝ”์ฝ” ํฌ์ฆˆ ๋ฐ์ดํ„ฐ ์„ธํŠธ

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์„ ์œ„ํ•ด ์„ค๊ณ„๋œ COCO(Common Objects in Context) ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ํŠน์ˆ˜ ๋ฒ„์ „์ž…๋‹ˆ๋‹ค. COCO ํ‚คํฌ์ธํŠธ 2017 ์ด๋ฏธ์ง€์™€ ๋ ˆ์ด๋ธ”์„ ํ™œ์šฉํ•˜์—ฌ ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์„ ์œ„ํ•œ YOLO ๊ฐ™์€ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

ํฌ์ฆˆ ์ƒ˜ํ”Œ ์ด๋ฏธ์ง€

์ฝ”์ฝ” ํฌ์ฆˆ ์‚ฌ์ „ ํ›ˆ๋ จ๋œ ๋ชจ๋ธ

๋ชจ๋ธ ํฌ๊ธฐ
(ํ”ฝ์…€)
mAPpose
50-95
mAPpose
50
์†๋„
CPU ONNX
(ms)
์†๋„
T4TensorRT10
(ms)
๋งค๊ฐœ๋ณ€์ˆ˜
(M)
FLOPs
(B)
YOLO11n-pose 640 50.0 81.0 52.4 ยฑ 0.5 1.7 ยฑ 0.0 2.9 7.6
YOLO11s-pose 640 58.9 86.3 90.5 ยฑ 0.6 2.6 ยฑ 0.0 9.9 23.2
YOLO11m-pose 640 64.9 89.4 187.3 ยฑ 0.8 4.9 ยฑ 0.1 20.9 71.7
YOLO11l-pose 640 66.1 89.9 247.7 ยฑ 1.1 6.4 ยฑ 0.1 26.2 90.7
YOLO11x-pose 640 69.5 91.1 488.0 ยฑ 13.9 12.1 ยฑ 0.2 58.8 203.3

์ฃผ์š” ๊ธฐ๋Šฅ

  • COCO-Pose๋Š” ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์„ ์œ„ํ•ด ํ‚คํฌ์ธํŠธ๋กœ ๋ ˆ์ด๋ธ”์ด ์ง€์ •๋œ 200๋งŒ ๊ฐœ์˜ ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋œ COCO ํ‚คํฌ์ธํŠธ 2017 ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•ฉ๋‹ˆ๋‹ค.
  • ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์ธ๋ฌผ์— ๋Œ€ํ•œ 17๊ฐœ์˜ ํ‚คํฌ์ธํŠธ๋ฅผ ์ง€์›ํ•˜์—ฌ ์„ธ๋ถ€์ ์ธ ํฌ์ฆˆ ์ถ”์ •์ด ์šฉ์ดํ•ฉ๋‹ˆ๋‹ค.
  • COCO์™€ ๋งˆ์ฐฌ๊ฐ€์ง€๋กœ ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์„ ์œ„ํ•œ ๊ฐ์ฒด ํ‚คํฌ์ธํŠธ ์œ ์‚ฌ์„ฑ(OKS)์„ ๋น„๋กฏํ•œ ํ‘œ์ค€ํ™”๋œ ํ‰๊ฐ€ ์ง€ํ‘œ๋ฅผ ์ œ๊ณตํ•˜๋ฏ€๋กœ ๋ชจ๋ธ ์„ฑ๋Šฅ์„ ๋น„๊ตํ•˜๋Š” ๋ฐ ์ ํ•ฉํ•ฉ๋‹ˆ๋‹ค.

๋ฐ์ดํ„ฐ ์„ธํŠธ ๊ตฌ์กฐ

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์„ธ ๊ฐœ์˜ ํ•˜์œ„ ์ง‘ํ•ฉ์œผ๋กœ ๋‚˜๋‰ฉ๋‹ˆ๋‹ค:

  1. Train2017: ์ด ํ•˜์œ„ ์ง‘ํ•ฉ์—๋Š” COCO ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ 118K ์ด๋ฏธ์ง€ ์ค‘ ์ผ๋ถ€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์œผ๋ฉฐ, ํฌ์ฆˆ ์ถ”์ • ๋ชจ๋ธ ํ•™์Šต์„ ์œ„ํ•ด ์ฃผ์„์ด ์ถ”๊ฐ€๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
  2. Val2017: ์ด ํ•˜์œ„ ์ง‘ํ•ฉ์—๋Š” ๋ชจ๋ธ ํ•™์Šต ์ค‘ ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ ๋ชฉ์ ์œผ๋กœ ์‚ฌ์šฉ๋˜๋Š” ์ด๋ฏธ์ง€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
  3. Test2017: ์ด ํ•˜์œ„ ์ง‘ํ•ฉ์€ ํ•™์Šต๋œ ๋ชจ๋ธ์„ ํ…Œ์ŠคํŠธํ•˜๊ณ  ๋ฒค์น˜๋งˆํ‚นํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ์ด๋ฏธ์ง€๋กœ ๊ตฌ์„ฑ๋ฉ๋‹ˆ๋‹ค. ์ด ํ•˜์œ„ ์ง‘ํ•ฉ์— ๋Œ€ํ•œ ์‹ค์ธก ์ž๋ฃŒ ์ฃผ์„์€ ๊ณต๊ฐœ๋˜์ง€ ์•Š์œผ๋ฉฐ, ๊ฒฐ๊ณผ๋Š” ์„ฑ๋Šฅ ํ‰๊ฐ€๋ฅผ ์œ„ํ•ด COCO ํ‰๊ฐ€ ์„œ๋ฒ„์— ์ œ์ถœ๋ฉ๋‹ˆ๋‹ค.

์• ํ”Œ๋ฆฌ์ผ€์ด์…˜

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ํŠนํžˆ OpenPose์™€ ๊ฐ™์€ ํ‚คํฌ์ธํŠธ ๊ฐ์ง€ ๋ฐ ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์—์„œ ๋”ฅ๋Ÿฌ๋‹ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๊ณ  ํ‰๊ฐ€ํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋ฉ๋‹ˆ๋‹ค. ์ด ๋ฐ์ดํ„ฐ ์„ธํŠธ์—๋Š” ์ˆ˜๋งŽ์€ ์ฃผ์„์ด ๋‹ฌ๋ฆฐ ์ด๋ฏธ์ง€์™€ ํ‘œ์ค€ํ™”๋œ ํ‰๊ฐ€ ๋ฉ”ํŠธ๋ฆญ์ด ํฌํ•จ๋˜์–ด ์žˆ์–ด ํฌ์ฆˆ ์ถ”์ •์— ์ค‘์ ์„ ๋‘” ์ปดํ“จํ„ฐ ๋น„์ „ ์—ฐ๊ตฌ์ž์™€ ์‹ค๋ฌด์ž์—๊ฒŒ ํ•„์ˆ˜์ ์ธ ๋ฆฌ์†Œ์Šค์ž…๋‹ˆ๋‹ค.

๋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. COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๊ฒฝ์šฐ, ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ coco-pose.yaml ํŒŒ์ผ์€ ๋‹ค์Œ ์œ„์น˜์—์„œ ์œ ์ง€๋ฉ๋‹ˆ๋‹ค. https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/coco-pose.yaml.

ultralytics/cfg/datasets/coco-pose.yaml

# Ultralytics YOLO ๐Ÿš€, AGPL-3.0 license
# COCO 2017 dataset https://cocodataset.org by Microsoft
# Documentation: https://docs.ultralytics.com/datasets/pose/coco/
# Example usage: yolo train data=coco-pose.yaml
# parent
# โ”œโ”€โ”€ ultralytics
# โ””โ”€โ”€ datasets
#     โ””โ”€โ”€ coco-pose  โ† downloads here (20.1 GB)

# 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/coco-pose # dataset root dir
train: train2017.txt # train images (relative to 'path') 118287 images
val: val2017.txt # val images (relative to 'path') 5000 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794

# Keypoints
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]

# Classes
names:
  0: person

# Download script/URL (optional)
download: |
  from ultralytics.utils.downloads import download
  from pathlib import Path

  # Download labels
  dir = Path(yaml['path'])  # dataset root dir
  url = 'https://github.com/ultralytics/assets/releases/download/v0.0.0/'
  urls = [url + 'coco2017labels-pose.zip']  # labels
  download(urls, dir=dir.parent)
  # Download data
  urls = ['http://images.cocodataset.org/zips/train2017.zip',  # 19G, 118k images
          'http://images.cocodataset.org/zips/val2017.zip',  # 1G, 5k images
          'http://images.cocodataset.org/zips/test2017.zip']  # 7G, 41k images (optional)
  download(urls, dir=dir / 'images', threads=3)

์‚ฌ์šฉ๋ฒ•

์ด๋ฏธ์ง€ ํฌ๊ธฐ๊ฐ€ 640์ธ 100๊ฐœ์˜ ์—ํฌํฌ์— ๋Œ€ํ•ด COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ YOLO11n ํฌ์ฆˆ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ๋‹ค์Œ ์ฝ”๋“œ ์กฐ๊ฐ์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ์ธ์ˆ˜์˜ ์ „์ฒด ๋ชฉ๋ก์€ ๋ชจ๋ธ ํ›ˆ๋ จ ํŽ˜์ด์ง€๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์—ด์ฐจ ์˜ˆ์‹œ

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-pose.pt")  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data="coco-pose.yaml", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo pose train data=coco-pose.yaml model=yolo11n-pose.pt epochs=100 imgsz=640

์ƒ˜ํ”Œ ์ด๋ฏธ์ง€ ๋ฐ ์ฃผ์„

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์—๋Š” ํ‚คํฌ์ธํŠธ๋กœ ์ฃผ์„์ด ๋‹ฌ๋ฆฐ ๋‹ค์–‘ํ•œ ์ด๋ฏธ์ง€ ์„ธํŠธ๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค. ๋‹ค์Œ์€ ํ•ด๋‹น ์ฃผ์„๊ณผ ํ•จ๊ป˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ด๋ฏธ์ง€ ๋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 ์˜ˆ๋Š” COCO-Pose ๋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‘์—…์— COCO-Pose ๋ฐ์ดํ„ฐ์…‹์„ ์‚ฌ์šฉํ•˜๋Š” ๊ฒฝ์šฐ ๋‹ค์Œ ๋…ผ๋ฌธ์„ ์ธ์šฉํ•ด ์ฃผ์„ธ์š”:

@misc{lin2015microsoft,
      title={Microsoft COCO: Common Objects in Context},
      author={Tsung-Yi Lin and Michael Maire and Serge Belongie and Lubomir Bourdev and Ross Girshick and James Hays and Pietro Perona and Deva Ramanan and C. Lawrence Zitnick and Piotr Dollรกr},
      year={2015},
      eprint={1405.0312},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

์ปดํ“จํ„ฐ ๋น„์ „ ์ปค๋ฎค๋‹ˆํ‹ฐ๋ฅผ ์œ„ํ•ด ์ด ๊ท€์ค‘ํ•œ ๋ฆฌ์†Œ์Šค๋ฅผ ๋งŒ๋“ค๊ณ  ์œ ์ง€ ๊ด€๋ฆฌํ•ด ์ฃผ์‹  COCO ์ปจ์†Œ์‹œ์—„์— ๊ฐ์‚ฌ์˜ ๋ง์”€์„ ์ „ํ•ฉ๋‹ˆ๋‹ค. COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ์ œ์ž‘์ž์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ COCO ๋ฐ์ดํ„ฐ ์„ธํŠธ ์›น์‚ฌ์ดํŠธ๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

์ž์ฃผ ๋ฌป๋Š” ์งˆ๋ฌธ

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ๋ฌด์—‡์ด๋ฉฐ, ํฌ์ฆˆ ์ถ”์ •์— Ultralytics YOLO ์–ด๋–ป๊ฒŒ ์‚ฌ์šฉ๋˜๋‚˜์š”?

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์„ ์œ„ํ•ด ์„ค๊ณ„๋œ COCO(Common Objects in Context) ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ํŠน์ˆ˜ ๋ฒ„์ „์ž…๋‹ˆ๋‹ค. COCO ํ‚คํฌ์ธํŠธ 2017 ์ด๋ฏธ์ง€์™€ ์ฃผ์„์„ ๊ธฐ๋ฐ˜์œผ๋กœ ๊ตฌ์ถ•๋˜์–ด ์ž์„ธํ•œ ํฌ์ฆˆ ์ถ”์ •์„ ์œ„ํ•ด Ultralytics YOLO ๊ฐ™์€ ๋ชจ๋ธ์„ ํ•™์Šตํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด, COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ์‚ฌ์ „ ํ›ˆ๋ จ๋œ ๋ชจ๋ธ์„ ๋กœ๋“œํ•˜๊ณ  YAML ๊ตฌ์„ฑ์œผ๋กœ ํ›ˆ๋ จํ•˜์—ฌ YOLO11n ํฌ์ฆˆ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ํ›ˆ๋ จ ์˜ˆ์ œ๋Š” ํ›ˆ๋ จ ๋ฌธ์„œ๋ฅผ ์ฐธ์กฐํ•˜์„ธ์š”.

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ YOLO11 ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ์–ด๋–ป๊ฒŒ ํ•ด์•ผ ํ•˜๋‚˜์š”?

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์— ๋Œ€ํ•œ YOLO11 ๋ชจ๋ธ ํ›ˆ๋ จ์€ Python ๋˜๋Š” CLI ๋ช…๋ น์„ ์‚ฌ์šฉํ•˜์—ฌ ์ˆ˜ํ–‰ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด ์ด๋ฏธ์ง€ ํฌ๊ธฐ๊ฐ€ 640์ธ 100๊ฐœ์˜ ์—ํฌํฌ์— ๋Œ€ํ•ด YOLO11n ํฌ์ฆˆ ๋ชจ๋ธ์„ ํ›ˆ๋ จํ•˜๋ ค๋ฉด ๋‹ค์Œ ๋‹จ๊ณ„๋ฅผ ๋”ฐ๋ฅด์„ธ์š”:

์—ด์ฐจ ์˜ˆ์‹œ

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-pose.pt")  # load a pretrained model (recommended for training)

# Train the model
results = model.train(data="coco-pose.yaml", epochs=100, imgsz=640)
# Start training from a pretrained *.pt model
yolo pose train data=coco-pose.yaml model=yolo11n-pose.pt epochs=100 imgsz=640

๊ต์œก ๊ณผ์ • ๋ฐ ์‚ฌ์šฉ ๊ฐ€๋Šฅํ•œ ์ธ์ˆ˜์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ ๊ต์œก ํŽ˜์ด์ง€์—์„œ ํ™•์ธํ•˜์„ธ์š”.

๋ชจ๋ธ ์„ฑ๋Šฅ์„ ํ‰๊ฐ€ํ•˜๊ธฐ ์œ„ํ•ด COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์—์„œ ์ œ๊ณตํ•˜๋Š” ๋‹ค์–‘ํ•œ ์ง€ํ‘œ์—๋Š” ์–ด๋–ค ๊ฒƒ์ด ์žˆ๋‚˜์š”?

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์›๋ž˜ COCO ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ์œ ์‚ฌํ•˜๊ฒŒ ํฌ์ฆˆ ์ถ”์ • ์ž‘์—…์— ๋Œ€ํ•œ ๋ช‡ ๊ฐ€์ง€ ํ‘œ์ค€ํ™”๋œ ํ‰๊ฐ€ ์ง€ํ‘œ๋ฅผ ์ œ๊ณตํ•ฉ๋‹ˆ๋‹ค. ์ฃผ์š” ๋ฉ”ํŠธ๋ฆญ์—๋Š” ๊ธฐ์ค€์  ์ฃผ์„์— ๋Œ€ํ•ด ์˜ˆ์ธก๋œ ํ‚คํฌ์ธํŠธ์˜ ์ •ํ™•๋„๋ฅผ ํ‰๊ฐ€ํ•˜๋Š” ๊ฐ์ฒด ํ‚คํฌ์ธํŠธ ์œ ์‚ฌ๋„(OKS)๊ฐ€ ํฌํ•จ๋ฉ๋‹ˆ๋‹ค. ์ด๋Ÿฌํ•œ ๋ฉ”ํŠธ๋ฆญ์„ ํ†ตํ•ด ์„œ๋กœ ๋‹ค๋ฅธ ๋ชจ๋ธ ๊ฐ„์˜ ์ฒ ์ €ํ•œ ์„ฑ๋Šฅ ๋น„๊ต๊ฐ€ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค. ์˜ˆ๋ฅผ ๋“ค์–ด, YOLO11n-pose, YOLO11s-pose ๋“ฑ๊ณผ ๊ฐ™์€ COCO-Pose ์‚ฌ์ „ ํ•™์Šต ๋ชจ๋ธ์—๋Š” mAPpose50-95๋ฐ mAPpose50๊ณผ๊ฐ™์€ ํŠน์ • ์„ฑ๋Šฅ ๋ฉ”ํŠธ๋ฆญ์ด ๋ฌธ์„œ์— ๋‚˜์—ด๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์–ด๋–ป๊ฒŒ ๊ตฌ์กฐํ™”๋˜๊ณ  ๋ถ„ํ• ๋˜๋‚˜์š”?

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์„ธ ๊ฐœ์˜ ํ•˜์œ„ ์ง‘ํ•ฉ์œผ๋กœ ๋‚˜๋‰ฉ๋‹ˆ๋‹ค:

  1. Train2017: ํฌ์ฆˆ ์ถ”์ • ๋ชจ๋ธ ํ•™์Šต์„ ์œ„ํ•ด ์ฃผ์„์ด ๋‹ฌ๋ฆฐ 118K COCO ์ด๋ฏธ์ง€์˜ ์ผ๋ถ€๊ฐ€ ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
  2. Val2017: ๋ชจ๋ธ ํ•™์Šต ์ค‘ ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ๋ฅผ ์œ„ํ•ด ์„ ํƒํ•œ ์ด๋ฏธ์ง€์ž…๋‹ˆ๋‹ค.
  3. Test2017: ํ•™์Šต๋œ ๋ชจ๋ธ์„ ํ…Œ์ŠคํŠธํ•˜๊ณ  ๋ฒค์น˜๋งˆํ‚นํ•˜๋Š” ๋ฐ ์‚ฌ์šฉ๋˜๋Š” ์ด๋ฏธ์ง€์ž…๋‹ˆ๋‹ค. ์ด ํ•˜์œ„ ์ง‘ํ•ฉ์— ๋Œ€ํ•œ ์‹ค์ธก ๋ฐ์ดํ„ฐ ์ฃผ์„์€ ๊ณต๊ฐœ๋˜์ง€ ์•Š์œผ๋ฉฐ, ๊ฒฐ๊ณผ๋Š” ์„ฑ๋Šฅ ํ‰๊ฐ€๋ฅผ ์œ„ํ•ด COCO ํ‰๊ฐ€ ์„œ๋ฒ„์— ์ œ์ถœ๋ฉ๋‹ˆ๋‹ค.

์ด๋Ÿฌํ•œ ํ•˜์œ„ ์ง‘ํ•ฉ์€ ๊ต์œก, ์œ ํšจ์„ฑ ๊ฒ€์‚ฌ ๋ฐ ํ…Œ์ŠคํŠธ ๋‹จ๊ณ„๋ฅผ ํšจ๊ณผ์ ์œผ๋กœ ๊ตฌ์„ฑํ•˜๋Š” ๋ฐ ๋„์›€์ด ๋ฉ๋‹ˆ๋‹ค. ๊ตฌ์„ฑ์— ๋Œ€ํ•œ ์ž์„ธํ•œ ๋‚ด์šฉ์€ coco-pose.yaml ํŒŒ์ผ์€ GitHub.

์ฝ”์ฝ”ํฌ์ฆˆ ๋ฐ์ดํ„ฐ ์„ธํŠธ์˜ ์ฃผ์š” ํŠน์ง•๊ณผ ํ™œ์šฉ ๋ถ„์•ผ๋Š” ๋ฌด์—‡์ธ๊ฐ€์š”?

COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” COCO ํ‚คํฌ์ธํŠธ 2017 ์ฃผ์„์„ ํ™•์žฅํ•˜์—ฌ ์ธ๋ฌผ์— ๋Œ€ํ•œ 17๊ฐœ์˜ ํ‚คํฌ์ธํŠธ๋ฅผ ํฌํ•จํ•จ์œผ๋กœ์จ ์ƒ์„ธํ•œ ํฌ์ฆˆ๋ฅผ ์ถ”์ •ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค. ํ‘œ์ค€ํ™”๋œ ํ‰๊ฐ€ ์ง€ํ‘œ(์˜ˆ: OKS)๋ฅผ ํ†ตํ•ด ๋‹ค์–‘ํ•œ ๋ชจ๋ธ ๊ฐ„์˜ ๋น„๊ต๊ฐ€ ์šฉ์ดํ•ฉ๋‹ˆ๋‹ค. COCO-Pose ๋ฐ์ดํ„ฐ ์„ธํŠธ๋Š” ์Šคํฌ์ธ  ๋ถ„์„, ํ—ฌ์Šค์ผ€์–ด, ์ธ๊ฐ„๊ณผ ์ปดํ“จํ„ฐ์˜ ์ƒํ˜ธ์ž‘์šฉ ๋“ฑ ์ธ๋ฌผ์˜ ์ƒ์„ธํ•œ ํฌ์ฆˆ ์ถ”์ •์ด ํ•„์š”ํ•œ ๋‹ค์–‘ํ•œ ์˜์—ญ์—์„œ ํ™œ์šฉ๋˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ์‹ค์ œ ์‚ฌ์šฉ ์‹œ, ๋ฌธ์„œ์— ์ œ๊ณต๋œ ๊ฒƒ๊ณผ ๊ฐ™์€ ์‚ฌ์ „ ํ›ˆ๋ จ๋œ ๋ชจ๋ธ(์˜ˆ: YOLO11n-pose)์„ ํ™œ์šฉํ•˜๋ฉด ํ”„๋กœ์„ธ์Šค๋ฅผ ํฌ๊ฒŒ ๊ฐ„์†Œํ™”ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค(์ฃผ์š” ๊ธฐ๋Šฅ).

์—ฐ๊ตฌ ๋˜๋Š” ๊ฐœ๋ฐœ ์ž‘์—…์— COCO-Pose ๋ฐ์ดํ„ฐ์„ธํŠธ๋ฅผ ์‚ฌ์šฉํ•˜๋Š” ๊ฒฝ์šฐ, ๋‹ค์Œ BibTeX ํ•ญ๋ชฉ์œผ๋กœ ๋…ผ๋ฌธ์„ ์ธ์šฉํ•ด ์ฃผ์„ธ์š”.

๐Ÿ“…1 ๋…„ ์ „ ์ƒ์„ฑ๋จ โœ๏ธ 1๊ฐœ์›” ์ „ ์—…๋ฐ์ดํŠธ๋จ

๋Œ“๊ธ€