高品質で代表性のあるデータを収集する

import shutil
from pathlib import Path

from ultralytics.data.utils import check_det_dataset, img2label_paths

data = check_det_dataset("coco128.yaml")  # 128 COCO images stand in for your camera captures
out = Path("datasets/practice")
(out / "images").mkdir(parents=True, exist_ok=True)
(out / "labels").mkdir(parents=True, exist_ok=True)

for i, image in enumerate(sorted(Path(data["train"]).glob("*.jpg"))):
    camera = ("cam1", "cam1", "cam2", "cam3", "cam4")[i % 5]  # cam1 over-collected, like a real site
    name = f"{camera}_2026-05-0{i // 32 + 1}_{i:06d}"  # camera, capture day, frame number
    shutil.copy(image, out / "images" / f"{name}.jpg")
    label = Path(img2label_paths([str(image)])[0])
    if label.exists():
        shutil.copy(label, out / "labels" / f"{name}.txt")

print(len(list((out / "images").glob("*.jpg"))), "images written to", out)

128 images written to datasets/practice

from collections import Counter
from pathlib import Path

QUOTA = {"cam1": 30, "cam2": 30, "cam3": 30, "cam4": 30}  # images per camera, from your spec

images = sorted(Path("datasets/practice/images").glob("*.jpg"))
cameras = Counter(p.stem.split("_")[0] for p in images)
days = Counter(p.stem.split("_")[1] for p in images)

for camera, quota in QUOTA.items():
    gap = quota - cameras[camera]
    print(f"{camera}: {cameras[camera]:3d} / {quota}  {'ok' if gap <= 0 else f'collect {gap} more'}")
print("days:", dict(sorted(days.items())))

cam1:  52 / 30  ok
cam2:  26 / 30  collect 4 more
cam3:  25 / 30  collect 5 more
cam4:  25 / 30  collect 5 more
days: {'2026-05-01': 32, '2026-05-02': 32, '2026-05-03': 32, '2026-05-04': 32}

from pathlib import Path

import cv2

from ultralytics.utils.downloads import safe_download

video = "solutions_ci_demo.mp4"  # a short public demo clip; swap in your own footage
safe_download(f"https://github.com/ultralytics/assets/releases/download/v0.0.0/{video}")
Path("frames").mkdir(exist_ok=True)

cap = cv2.VideoCapture(video)
fps = cap.get(cv2.CAP_PROP_FPS)
read = kept = 0
last = None
while True:
    ok, frame = cap.read()
    if not ok:
        break
    thumb = cv2.cvtColor(cv2.resize(frame, (64, 64)), cv2.COLOR_BGR2GRAY).astype(float)
    if last is None or abs(thumb - last).mean() > 10:  # keep a frame only when the scene has changed
        cv2.imwrite(f"frames/clip01_{read:06d}.jpg", frame)  # the clip ID stays in the filename
        kept, last = kept + 1, thumb
    read += 1

print(f"{read} frames at {fps:.0f} FPS -> {kept} kept")

62 frames at 30 FPS -> 6 kept