Files
sentinel-home-ai/fam-core/tools/backfill_frames.py
ericwyuan 8a333d752d feat: 历史事件关键帧补抽工具 backfill_frames.py
Edge 帧图注入上线前的旧事件无帧图,事件列表第一屏全是占位符。
按 frame_timestamp - event_start_time 偏移从原始视频抽帧补齐,
幂等可重跑。NAS ffmpeg41 无 image2 muxer,用 -f singlejpeg 输出。
实测补 11 事件 65 帧全部成功(2026-08-14 的 10 个事件视频已被
清理,无法补)。
2026-08-20 22:07:36 +08:00

157 lines
5.8 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""为历史事件补抽关键帧图(视频仍存于 NAS 时)
Edge 注入关键帧 base64 上线前落库的事件没有帧图,本脚本从原始视频
按 frame_timestamp - event_start_time 偏移重新抽帧,补齐到 UI 静态目录。
用法:
venv/bin/python tools/backfill_frames.py [--dry-run] [--event-id N]
特性:
- 幂等: 单帧文件已存在即跳过,帧数齐全的事件整条跳过
- NAS ffmpeg41 无 image2 muxer必须用 -f singlejpeg 输出 jpg
- 抽帧尺寸与 NAS 预压缩一致480p 等比缩放),-q:v 5 约 60-100KB/张
"""
import os
import re
import sys
import argparse
import subprocess
from datetime import datetime
sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(__file__)), '..', 'src'))
import pymysql
from fam_core.config_loader import load_config
FFMPEG = '/var/packages/CodecPack/target/bin/ffmpeg41'
def video_duration(path: str) -> float:
"""解析 ffmpeg header 里的 Duration无 ffprobe 环境)"""
try:
r = subprocess.run([FFMPEG, '-i', path], capture_output=True, text=True, timeout=60)
m = re.search(r'Duration:\s*(\d+):(\d+):(\d+)', r.stderr)
if m:
h, mi, s = (int(x) for x in m.groups())
return h * 3600 + mi * 60 + s
except Exception:
pass
return 0.0
def extract_frame(video: str, offset: float, out_path: str) -> bool:
cmd = [
FFMPEG, '-y',
'-ss', f'{offset:.1f}',
'-i', video,
'-frames:v', '1',
'-vf', 'scale=854:480:force_original_aspect_ratio=decrease,scale=trunc(iw/2)*2:trunc(ih/2)*2',
'-q:v', '5',
'-f', 'singlejpeg',
out_path,
]
try:
r = subprocess.run(cmd, capture_output=True, timeout=120)
return r.returncode == 0 and os.path.getsize(out_path) > 1024
except Exception:
return False
def main():
ap = argparse.ArgumentParser()
ap.add_argument('--dry-run', action='store_true', help='只统计不落盘')
ap.add_argument('--event-id', type=int, default=None, help='只处理指定事件')
args = ap.parse_args()
cfg = load_config()
frame_dir = cfg.get('storage', {}).get(
'frame_image_dir', '/volume1/web/sentinel-home-ai/fam-ui/static/frames')
db = cfg['database']
conn = pymysql.connect(
host=db.get('host', '127.0.0.1'),
port=db.get('port', 3306),
user=db.get('user', 'root'),
password=db.get('password', ''),
database=db.get('database', 'sentinel_home_ai'),
unix_socket=db.get('unix_socket'),
charset='utf8mb4',
cursorclass=pymysql.cursors.DictCursor,
)
try:
with conn.cursor() as cur:
sql = """
SELECT me.event_id, me.event_start_time, pt.video_path,
(SELECT COUNT(*) FROM event_details ed
WHERE ed.event_id = me.event_id) AS detail_count
FROM monitor_events me
LEFT JOIN process_tasks pt ON pt.task_id = me.task_id
"""
params = ()
if args.event_id:
sql += ' WHERE me.event_id = %s'
params = (args.event_id,)
sql += ' ORDER BY me.event_id'
cur.execute(sql, params)
events = cur.fetchall()
stat = {'skip_complete': 0, 'skip_no_video': 0, 'extracted': 0, 'failed': 0, 'events': 0}
for ev in events:
eid = ev['event_id']
edir = os.path.join(frame_dir, f'event_{eid}')
existing = {f for f in os.listdir(edir) if f.endswith('.jpg')} if os.path.isdir(edir) else set()
with conn.cursor() as cur:
cur.execute(
"""SELECT frame_index, frame_timestamp FROM event_details
WHERE event_id = %s ORDER BY frame_index""",
(eid,))
frames = cur.fetchall()
missing = [f for f in frames if f'frame_{f["frame_index"]}.jpg' not in existing]
if not missing:
stat['skip_complete'] += 1
continue
video = ev.get('video_path') or ''
if not video or not os.path.isfile(video):
print(f'[event {eid}] 视频不存在,跳过 {len(missing)} 帧: {video}')
stat['skip_no_video'] += 1
continue
dur = video_duration(video)
start = ev['event_start_time']
if isinstance(start, str):
start = datetime.strptime(start[:19], '%Y-%m-%d %H:%M:%S')
os.makedirs(edir, exist_ok=True)
stat['events'] += 1
print(f'[event {eid}] 补 {len(missing)}/{len(frames)} 帧 (视频 {os.path.basename(video)}, {dur:.0f}s)')
for f in missing:
out_path = os.path.join(edir, f'frame_{f["frame_index"]}.jpg')
ts = f['frame_timestamp']
if isinstance(ts, str):
ts = datetime.strptime(ts[:19], '%Y-%m-%d %H:%M:%S')
offset = (ts - start).total_seconds()
offset = max(1.0, min(offset, max(1.0, dur - 2)))
if args.dry_run:
print(f' dry-run frame_{f["frame_index"]} @ {offset:.0f}s')
continue
ok = extract_frame(video, offset, out_path)
stat['extracted' if ok else 'failed'] += 1
if not ok:
print(f' 失败 frame_{f["frame_index"]} @ {offset:.0f}s')
if os.path.exists(out_path):
os.remove(out_path)
print(f"\n完成: 事件 {stat['events']} 个已补 | 抽帧成功 {stat['extracted']} 失败 {stat['failed']} "
f"| 齐全跳过 {stat['skip_complete']} | 视频缺失跳过 {stat['skip_no_video']}")
finally:
conn.close()
if __name__ == '__main__':
main()