VisDrone ๋ฐ์ดํฐ ์ธํธ
The VisDrone Dataset is a large-scale benchmark created by the AISKYEYE team at the Lab of Machine Learning and Data Mining, Tianjin University, China. It contains carefully annotated ground truth data for various computer vision tasks related to drone-based image and video analysis.
Watch: ๋๋ก ์ด๋ฏธ์ง ๋ถ์์ ์ํ VisDrone ๋ฐ์ดํฐ ์ธํธ์ ๋ชจ๋ธ ํ๋ จ ๋ฐฉ๋ฒ Ultralytics YOLO
VisDrone์ ๋๋ก ์ ์ฅ์ฐฉ๋ ๋ค์ํ ์นด๋ฉ๋ผ๋ก ์ดฌ์ํ 261,908 ํ๋ ์์ 288๊ฐ ๋น๋์ค ํด๋ฆฝ๊ณผ 10,209๊ฐ์ ์ ์ ์ด๋ฏธ์ง๋ก ๊ตฌ์ฑ๋์ด ์์ต๋๋ค. ์ด ๋ฐ์ดํฐ ์ธํธ๋ ์์น(์ค๊ตญ ์ ์ญ์ 14๊ฐ ๋์), ํ๊ฒฝ(๋์ ๋ฐ ๋์ด), ๋ฌผ์ฒด(๋ณดํ์, ์ฐจ๋, ์์ ๊ฑฐ ๋ฑ), ๋ฐ๋(๋๋ฌธ๋๋ฌธ ๋ถ๋น๋ ์ฅ๋ฉด) ๋ฑ ๋ค์ํ ์ธก๋ฉด์ ํฌ๊ดํฉ๋๋ค. ๋ฐ์ดํฐ ์ธํธ๋ ๋ค์ํ ์๋๋ฆฌ์ค์ ๋ ์จ ๋ฐ ์กฐ๋ช ์กฐ๊ฑด์์ ๋ค์ํ ๋๋ก ํ๋ซํผ์ ์ฌ์ฉํ์ฌ ์์ง๋์์ต๋๋ค. ์ด๋ฌํ ํ๋ ์์๋ ๋ณดํ์, ์๋์ฐจ, ์์ ๊ฑฐ, ์ธ๋ฐ์์ ๊ฑฐ ๋ฑ 260๋ง ๊ฐ๊ฐ ๋๋ ๋์์ ๊ฒฝ๊ณ ์์์ ์๋์ผ๋ก ์ฃผ์์ ๋ฌ์์ต๋๋ค. ์ฌ ๊ฐ์์ฑ, ์ค๋ธ์ ํธ ํด๋์ค, ์คํด๋ฃจ์ ๊ณผ ๊ฐ์ ์์ฑ๋ ์ ๊ณต๋์ด ๋ฐ์ดํฐ ํ์ฉ๋๋ฅผ ๋์ผ ์ ์์ต๋๋ค.
๋ฐ์ดํฐ ์ธํธ ๊ตฌ์กฐ
VisDrone ๋ฐ์ดํฐ ์ธํธ๋ 5๊ฐ์ ์ฃผ์ ํ์ ์งํฉ์ผ๋ก ๊ตฌ์ฑ๋์ด ์์ผ๋ฉฐ, ๊ฐ ์งํฉ์ ํน์ ์์ ์ ์ค์ ์ ๋๊ณ ์์ต๋๋ค:
- ์์ 1: ์ด๋ฏธ์ง์์ ๋ฌผ์ฒด ๊ฐ์ง
- ์์ 2: ๋์์์์ ๊ฐ์ฒด ๊ฐ์ง
- ์์ 3: ๋จ์ผ ๊ฐ์ฒด ์ถ์
- ์์ 4: ๋ค์ค ๊ฐ์ฒด ์ถ์
- ์์ 5: ๊ตฐ์ค ๊ณ์ฐ
์ ํ๋ฆฌ์ผ์ด์
The VisDrone dataset is widely used for training and evaluating deep learning models in drone-based computer vision tasks such as object detection, object tracking, and crowd counting. The dataset's diverse set of sensor data, object annotations, and attributes make it a valuable resource for researchers and practitioners in the field of drone-based computer vision.
๋ฐ์ดํฐ ์ธํธ YAML
๋ฐ์ดํฐ ์ธํธ ๊ตฌ์ฑ์ ์ ์ํ๋ ๋ฐ๋ YAML(๋ ๋ค๋ฅธ ๋งํฌ์
์ธ์ด) ํ์ผ์ด ์ฌ์ฉ๋ฉ๋๋ค. ์ฌ๊ธฐ์๋ ๋ฐ์ดํฐ ์ธํธ์ ๊ฒฝ๋ก, ํด๋์ค ๋ฐ ๊ธฐํ ๊ด๋ จ ์ ๋ณด์ ๋ํ ์ ๋ณด๊ฐ ํฌํจ๋์ด ์์ต๋๋ค. Visdrone ๋ฐ์ดํฐ ์ธํธ์ ๊ฒฝ์ฐ, ๋ฐ์ดํฐ ์ธํธ์ VisDrone.yaml
ํ์ผ์ ๋ค์ ์์น์์ ์ ์ง๋ฉ๋๋ค. https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/VisDrone.yaml.
ultralytics/cfg/datasets/VisDrone.yaml
# Ultralytics YOLO ๐, AGPL-3.0 license
# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University
# Documentation: https://docs.ultralytics.com/datasets/detect/visdrone/
# Example usage: yolo train data=VisDrone.yaml
# parent
# โโโ ultralytics
# โโโ datasets
# โโโ VisDrone โ downloads here (2.3 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/VisDrone # dataset root dir
train: VisDrone2019-DET-train/images # train images (relative to 'path') 6471 images
val: VisDrone2019-DET-val/images # val images (relative to 'path') 548 images
test: VisDrone2019-DET-test-dev/images # test images (optional) 1610 images
# Classes
names:
0: pedestrian
1: people
2: bicycle
3: car
4: van
5: truck
6: tricycle
7: awning-tricycle
8: bus
9: motor
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import os
from pathlib import Path
from ultralytics.utils.downloads import download
def visdrone2yolo(dir):
from PIL import Image
from tqdm import tqdm
def convert_box(size, box):
# Convert VisDrone box to YOLO xywh box
dw = 1. / size[0]
dh = 1. / size[1]
return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
(dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory
pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
for f in pbar:
img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
lines = []
with open(f, 'r') as file: # read annotation.txt
for row in [x.split(',') for x in file.read().strip().splitlines()]:
if row[4] == '0': # VisDrone 'ignored regions' class 0
continue
cls = int(row[5]) - 1
box = convert_box(img_size, tuple(map(int, row[:4])))
lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
with open(str(f).replace(f'{os.sep}annotations{os.sep}', f'{os.sep}labels{os.sep}'), 'w') as fl:
fl.writelines(lines) # write label.txt
# Download
dir = Path(yaml['path']) # dataset root dir
urls = ['https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-train.zip',
'https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-val.zip',
'https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-test-dev.zip',
'https://github.com/ultralytics/assets/releases/download/v0.0.0/VisDrone2019-DET-test-challenge.zip']
download(urls, dir=dir, curl=True, threads=4)
# Convert
for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels
์ฌ์ฉ๋ฒ
To train a YOLO11n model on the VisDrone dataset for 100 epochs with an image size of 640, you can use the following code snippets. For a comprehensive list of available arguments, refer to the model Training page.
์ด์ฐจ ์์
์ํ ๋ฐ์ดํฐ ๋ฐ ์ฃผ์
VisDrone ๋ฐ์ดํฐ ์ธํธ์๋ ๋๋ก ์ ์ฅ์ฐฉ๋ ์นด๋ฉ๋ผ๋ก ์บก์ฒํ ๋ค์ํ ์ด๋ฏธ์ง์ ๋์์์ด ํฌํจ๋์ด ์์ต๋๋ค. ๋ค์์ ๋ฐ์ดํฐ ์ธํธ์ ๋ช ๊ฐ์ง ๋ฐ์ดํฐ ์์์ ํด๋น ์ฃผ์์ ๋๋ค:
- Task 1: Object detection in images - This image demonstrates an example of object detection in images, where objects are annotated with bounding boxes. The dataset provides a wide variety of images taken from different locations, environments, and densities to facilitate the development of models for this task.
์ด ์๋ VisDrone ๋ฐ์ดํฐ ์ธํธ์ ํฌํจ๋ ๋ฐ์ดํฐ์ ๋ค์์ฑ๊ณผ ๋ณต์ก์ฑ์ ๋ณด์ฌ์ฃผ๋ฉฐ ๋๋ก ๊ธฐ๋ฐ ์ปดํจํฐ ๋น์ ์์ ์์ ๊ณ ํ์ง ์ผ์ ๋ฐ์ดํฐ์ ์ค์์ฑ์ ๊ฐ์กฐํฉ๋๋ค.
์ธ์ฉ ๋ฐ ๊ฐ์ฌ
์ฐ๊ตฌ ๋๋ ๊ฐ๋ฐ ์์ ์ VisDrone ๋ฐ์ดํฐ์ธํธ๋ฅผ ์ฌ์ฉํ๋ ๊ฒฝ์ฐ ๋ค์ ๋ ผ๋ฌธ์ ์ธ์ฉํด ์ฃผ์ธ์:
@ARTICLE{9573394,
author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Detection and Tracking Meet Drones Challenge},
year={2021},
volume={},
number={},
pages={1-1},
doi={10.1109/TPAMI.2021.3119563}}
We would like to acknowledge the AISKYEYE team at the Lab of Machine Learning and Data Mining, Tianjin University, China, for creating and maintaining the VisDrone dataset as a valuable resource for the drone-based computer vision research community. For more information about the VisDrone dataset and its creators, visit the VisDrone Dataset GitHub repository.
์์ฃผ ๋ฌป๋ ์ง๋ฌธ
VisDrone ๋ฐ์ดํฐ ์ธํธ๋ ๋ฌด์์ด๋ฉฐ ์ฃผ์ ๊ธฐ๋ฅ์ ๋ฌด์์ธ๊ฐ์?
The VisDrone Dataset is a large-scale benchmark created by the AISKYEYE team at Tianjin University, China. It is designed for various computer vision tasks related to drone-based image and video analysis. Key features include:
- Composition: 288 video clips with 261,908 frames and 10,209 static images.
- Annotations: Over 2.6 million bounding boxes for objects like pedestrians, cars, bicycles, and tricycles.
- Diversity: Collected across 14 cities, in urban and rural settings, under different weather and lighting conditions.
- Tasks: Split into five main tasksโobject detection in images and videos, single-object and multi-object tracking, and crowd counting.
How can I use the VisDrone Dataset to train a YOLO11 model with Ultralytics?
To train a YOLO11 model on the VisDrone dataset for 100 epochs with an image size of 640, you can follow these steps:
์ด์ฐจ ์์
์ถ๊ฐ ๊ตฌ์ฑ ์ต์ ์ ๋ชจ๋ธ ๊ต์ก ํ์ด์ง๋ฅผ ์ฐธ์กฐํ์ธ์.
VisDrone ๋ฐ์ดํฐ ์ธํธ์ ์ฃผ์ ํ์ ์งํฉ๊ณผ ๊ทธ ์ ํ๋ฆฌ์ผ์ด์ ์ ๋ฌด์์ธ๊ฐ์?
The VisDrone dataset is divided into five main subsets, each tailored for a specific computer vision task:
- Task 1: Object detection in images.
- Task 2: Object detection in videos.
- Task 3: Single-object tracking.
- Task 4: Multi-object tracking.
- Task 5: Crowd counting.
These subsets are widely used for training and evaluating deep learning models in drone-based applications such as surveillance, traffic monitoring, and public safety.
VisDrone ๋ฐ์ดํฐ ์ธํธ์ ๊ตฌ์ฑ ํ์ผ์ Ultralytics ์์ ์ด๋์์ ์ฐพ์ ์ ์๋์?
VisDrone ๋ฐ์ดํฐ ์ธํธ์ ๊ตฌ์ฑ ํ์ผ์
๋๋ค, VisDrone.yaml
๋ ๋ค์ ๋งํฌ์ Ultralytics ๋ฆฌํฌ์งํ ๋ฆฌ์์ ์ฐพ์ ์ ์์ต๋๋ค:
VisDrone.yaml.
๋ด ์ฐ๊ตฌ์ VisDrone ๋ฐ์ดํฐ์ธํธ๋ฅผ ์ฌ์ฉํ๋ ๊ฒฝ์ฐ ์ด๋ป๊ฒ ์ธ์ฉํ ์ ์๋์?
์ฐ๊ตฌ ๋๋ ๊ฐ๋ฐ ์์ ์ VisDrone ๋ฐ์ดํฐ์ธํธ๋ฅผ ์ฌ์ฉํ๋ ๊ฒฝ์ฐ ๋ค์ ๋ ผ๋ฌธ์ ์ธ์ฉํด ์ฃผ์ธ์:
@ARTICLE{9573394,
author={Zhu, Pengfei and Wen, Longyin and Du, Dawei and Bian, Xiao and Fan, Heng and Hu, Qinghua and Ling, Haibin},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Detection and Tracking Meet Drones Challenge},
year={2021},
volume={},
number={},
pages={1-1},
doi={10.1109/TPAMI.2021.3119563}
}