Files
guitar_score/dump_frames.py
quantlab 98381d2893 feat(pipeline): v3-v4 dedup + panorama stitching + 1080p support
- HSV-aware _trim_to_content (white ratio 30-97%)
- pHash cluster dedup: dHash 32x32(1024bit), max_hamming=20
- Panoramic stitching: template matching scroll offset detection
- 4-stage pipeline: MSE -> Panorama -> pHash
- 1080p download priority + MAX_FRAME_WIDTH=1280 cap
- test_pipeline.py with YouTube URLs and --download mode
- 3 new known-issues documented
- devlog + STATUS.md updated
2026-03-25 21:58:48 +09:00

34 lines
1.1 KiB
Python

"""원본 프레임 덤프 — 각 영상에서 5개 프레임을 랜덤 추출"""
import sys
if sys.platform == "win32":
sys.stdout.reconfigure(encoding="utf-8", errors="replace")
import cv2
import numpy as np
from pathlib import Path
output = Path("output")
dump_dir = output / "raw_dump"
dump_dir.mkdir(exist_ok=True)
mp4s = sorted(output.glob("*.mp4"))
for vi, mp4 in enumerate(mp4s):
cap = cv2.VideoCapture(str(mp4))
total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
fps = cap.get(cv2.CAP_PROP_FPS)
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
print(f"Video {vi+1}: {mp4.name[:30]}... ({w}x{h}, {fps:.0f}fps, {total} frames)")
# 균등 간격으로 5개 프레임
indices = np.linspace(total * 0.1, total * 0.9, 5, dtype=int)
for i, idx in enumerate(indices):
cap.set(cv2.CAP_PROP_POS_FRAMES, idx)
ret, frame = cap.read()
if ret:
path = dump_dir / f"v{vi+1}_raw_{i}.png"
cv2.imwrite(str(path), frame)
print(f" frame {idx}{path.name} ({frame.shape})")
cap.release()
print(f"\n덤프 완료: {dump_dir}")