feat: 新增视频分析流水线、Web界面、孤儿清理工具;修复健壮性问题

- 新增 analysis/ 模块:MOG2活动检测、YOLO人物跟踪、MediaPipe摔倒检测、Ollama活动打标、缩略图抽取
- 新增 webapp/:Flask事件浏览界面,按需HEVC→H264转码缓存
- 新增 analyze.py:7阶段状态机流水线(scan→backfill→motion→person→fall→activity→thumbnail)
- 新增 cleanup_orphans.py:清理文件已删除的数据库孤儿记录
- 修复:motion/person/activity三阶段加单视频异常兜底,避免批次中断
- 修复:ollama_client加健康检查和3次重试,num_ctx从8192降到2048
- 修复:transcode_cache加fcntl文件锁,防止并发转码同一视频
- 修复:SQLite开WAL模式+busy_timeout,支持读写并发
- 修复:sync.py ffmpeg路径改为shutil.which查找,删除automate.py死代码PYTHON
- 修复:thumbnail失败加3次重试上限,避免无限重试损坏文件
- 新增:requirements.lock锁定版本、README文档
- 更新:.gitignore排除.playwright-mcp、截图、备份文件
This commit is contained in:
yuming
2026-09-18 15:52:49 +08:00
parent 203cca42a2
commit b3608f534e
31 changed files with 2792 additions and 27 deletions
+106
View File
@@ -0,0 +1,106 @@
"""本地事件展示网页:纯只读查询 analysis.db + 播放原始录像文件,
不写入任何数据,可以在 analyze.py 跑到一半时随时启动查看已完成的部分。
"""
from flask import Flask, jsonify, render_template, request, send_file
from analysis.config import PROJECT_ROOT
from analysis.db import get_connection
from webapp import transcode_cache
app = Flask(__name__)
EVENT_TYPES = ["person_presence", "fall", "activity"]
@app.route("/")
def index():
return render_template("index.html")
@app.route("/api/events")
def api_events():
event_type = request.args.get("event_type")
capture_date = request.args.get("date") # YYYYMMDD
query = """
SELECT e.id, e.video_id, e.event_type, e.label, e.start_offset_sec,
e.end_offset_sec, e.timestamp_abs, e.confidence, e.thumbnail_path,
v.capture_date, v.file_name
FROM events e JOIN videos v ON v.id = e.video_id
WHERE 1=1
"""
params = []
if event_type in EVENT_TYPES:
query += " AND e.event_type = ?"
params.append(event_type)
if capture_date:
query += " AND v.capture_date = ?"
params.append(capture_date)
query += " ORDER BY e.timestamp_abs DESC, e.id DESC LIMIT 500"
with get_connection() as conn:
rows = conn.execute(query, params).fetchall()
events = [
{
"id": r["id"],
"video_id": r["video_id"],
"event_type": r["event_type"],
"label": r["label"],
"start_offset_sec": r["start_offset_sec"],
"end_offset_sec": r["end_offset_sec"],
"timestamp_abs": r["timestamp_abs"],
"confidence": r["confidence"],
"capture_date": r["capture_date"],
"file_name": r["file_name"],
"thumbnail_url": f"/media/thumb/{r['id']}" if r["thumbnail_path"] else None,
}
for r in rows
]
return jsonify(events)
@app.route("/api/stats")
def api_stats():
with get_connection() as conn:
rows = conn.execute(
"SELECT event_type, COUNT(*) AS c FROM events GROUP BY event_type"
).fetchall()
return jsonify({r["event_type"]: r["c"] for r in rows})
@app.route("/media/<int:video_id>/stream")
def media_stream(video_id):
with get_connection() as conn:
row = conn.execute("SELECT file_path FROM videos WHERE id = ?", (video_id,)).fetchone()
if row is None:
return "视频不存在", 404
try:
play_path = transcode_cache.ensure_transcoded(video_id, PROJECT_ROOT / row["file_path"])
except RuntimeError as e:
return f"转码失败:{e}", 500
return send_file(play_path, conditional=True)
@app.route("/api/cache/stats")
def api_cache_stats():
return jsonify(transcode_cache.cache_stats())
@app.route("/api/cache/clear", methods=["POST"])
def api_cache_clear():
return jsonify(transcode_cache.clear_cache())
@app.route("/media/thumb/<int:event_id>")
def media_thumb(event_id):
with get_connection() as conn:
row = conn.execute("SELECT thumbnail_path FROM events WHERE id = ?", (event_id,)).fetchone()
if row is None or not row["thumbnail_path"]:
return "缩略图不存在", 404
return send_file(PROJECT_ROOT / row["thumbnail_path"], conditional=True)
if __name__ == "__main__":
app.run(host="127.0.0.1", port=5050, debug=False)
+108
View File
@@ -0,0 +1,108 @@
const eventTypeFilter = document.getElementById("event-type-filter");
const dateFilter = document.getElementById("date-filter");
const eventList = document.getElementById("event-list");
const player = document.getElementById("player");
const playerInfo = document.getElementById("player-info");
const statsEl = document.getElementById("stats");
const cacheInfoEl = document.getElementById("cache-info");
const clearCacheBtn = document.getElementById("clear-cache-btn");
const EVENT_TYPE_LABELS = {
person_presence: "人物出现",
fall: "摔倒",
activity: "活动",
};
function formatEventLabel(event) {
const typeName = EVENT_TYPE_LABELS[event.event_type] || event.event_type;
return event.label ? `${typeName} · ${event.label}` : typeName;
}
async function loadStats() {
const res = await fetch("/api/stats");
const stats = await res.json();
const parts = Object.entries(stats).map(
([type, count]) => `${EVENT_TYPE_LABELS[type] || type}: ${count}`
);
statsEl.textContent = parts.join(" | ");
}
function formatBytes(bytes) {
if (bytes < 1024 * 1024) return `${(bytes / 1024).toFixed(1)} KB`;
if (bytes < 1024 * 1024 * 1024) return `${(bytes / 1024 / 1024).toFixed(1)} MB`;
return `${(bytes / 1024 / 1024 / 1024).toFixed(2)} GB`;
}
async function loadCacheStats() {
const res = await fetch("/api/cache/stats");
const stats = await res.json();
cacheInfoEl.textContent = `转码缓存:${stats.file_count} 个文件,共占用 ${formatBytes(stats.total_size_bytes)}`;
}
clearCacheBtn.addEventListener("click", async () => {
if (!confirm("确认清空所有转码缓存吗?清空后再次播放这些视频需要重新转码。")) return;
const res = await fetch("/api/cache/clear", { method: "POST" });
const result = await res.json();
alert(`已清理 ${result.deleted} 个文件,释放 ${formatBytes(result.freed_bytes)} 空间`);
loadCacheStats();
});
async function loadEvents() {
const params = new URLSearchParams();
if (eventTypeFilter.value) params.set("event_type", eventTypeFilter.value);
if (dateFilter.value) params.set("date", dateFilter.value.replaceAll("-", ""));
const res = await fetch(`/api/events?${params.toString()}`);
const events = await res.json();
renderEventList(events);
}
function renderEventList(events) {
eventList.innerHTML = "";
for (const event of events) {
const item = document.createElement("div");
item.className = "event-item";
const thumb = document.createElement("img");
thumb.className = "event-thumb";
thumb.alt = formatEventLabel(event);
if (event.thumbnail_url) thumb.src = event.thumbnail_url;
const info = document.createElement("div");
info.className = "event-info";
info.innerHTML = `
<div class="event-type">${formatEventLabel(event)}</div>
<div class="event-time">${event.timestamp_abs || event.capture_date}</div>
`;
item.appendChild(thumb);
item.appendChild(info);
item.addEventListener("click", () => playEvent(event));
eventList.appendChild(item);
}
}
function playEvent(event) {
const isSameVideo = player.dataset.videoId === String(event.video_id);
player.dataset.videoId = event.video_id;
const seekAndPlay = () => {
player.currentTime = event.start_offset_sec || 0;
player.play();
};
if (isSameVideo) {
seekAndPlay();
} else {
player.src = `/media/${event.video_id}/stream`;
player.addEventListener("loadedmetadata", () => { seekAndPlay(); loadCacheStats(); }, { once: true });
}
playerInfo.textContent = `${event.file_name} · ${formatEventLabel(event)}`;
}
eventTypeFilter.addEventListener("change", loadEvents);
dateFilter.addEventListener("change", loadEvents);
loadStats();
loadCacheStats();
loadEvents();
+96
View File
@@ -0,0 +1,96 @@
body {
font-family: -apple-system, "PingFang SC", sans-serif;
margin: 20px;
color: #222;
}
.filters {
margin-bottom: 16px;
display: flex;
gap: 16px;
align-items: center;
}
#stats {
color: #666;
font-size: 0.9em;
}
.cache-panel {
margin-bottom: 16px;
display: flex;
gap: 12px;
align-items: center;
color: #666;
font-size: 0.9em;
}
.cache-panel button {
cursor: pointer;
}
.main {
display: flex;
gap: 20px;
}
.player-panel {
flex: 1;
}
#player {
width: 100%;
max-width: 640px;
background: #000;
}
#player-info {
margin-top: 8px;
color: #555;
font-size: 0.9em;
}
.event-list {
flex: 1;
max-height: 80vh;
overflow-y: auto;
display: flex;
flex-direction: column;
gap: 8px;
}
.event-item {
display: flex;
gap: 10px;
cursor: pointer;
padding: 6px;
border-radius: 6px;
}
.event-item:hover {
background: #f0f0f0;
}
.event-thumb {
width: 120px;
height: 68px;
object-fit: cover;
background: #ddd;
border-radius: 4px;
flex-shrink: 0;
}
.event-info {
display: flex;
flex-direction: column;
justify-content: center;
}
.event-type {
font-weight: 600;
}
.event-time {
color: #666;
font-size: 0.9em;
}
+41
View File
@@ -0,0 +1,41 @@
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>录像事件回放</title>
<link rel="stylesheet" href="{{ url_for('static', filename='style.css') }}">
</head>
<body>
<h1>录像事件回放</h1>
<div class="filters">
<label>事件类型
<select id="event-type-filter">
<option value="">全部</option>
<option value="person_presence">人物出现</option>
<option value="fall">摔倒</option>
<option value="activity">活动</option>
</select>
</label>
<label>日期
<input type="date" id="date-filter">
</label>
<span id="stats"></span>
</div>
<div class="cache-panel">
<span id="cache-info"></span>
<button id="clear-cache-btn">清空转码缓存</button>
</div>
<div class="main">
<div class="player-panel">
<video id="player" controls></video>
<div id="player-info"></div>
</div>
<div id="event-list" class="event-list"></div>
</div>
<script src="{{ url_for('static', filename='app.js') }}"></script>
</body>
</html>
+96
View File
@@ -0,0 +1,96 @@
"""网页播放的按需转码缓存:源文件mp4容器HEVC轨道sample entry编码标签缺失,
浏览器<video>标签无法识别,第一次点击播放时用ffmpeg(VideoToolbox硬件加速)转码成
标准H264并缓存到 TRANSCODED_DIR,之后复用缓存不重复转码;不预先转码全部录像。
"""
import fcntl
import subprocess
from pathlib import Path
from analysis.config import TRANSCODED_DIR
def cached_path(video_id):
return TRANSCODED_DIR / f"{video_id}.mp4"
def _lock_path(video_id):
return TRANSCODED_DIR / f"{video_id}.lock"
def ensure_transcoded(video_id, source_path):
"""返回可直接播放的文件路径。已有缓存直接复用,否则先转码再缓存。
用 fcntl 文件锁防止两个请求同时转码同一个视频:先到的转码,后到的等锁释放后
直接读缓存。锁文件在转码完成后删除。
"""
output_path = cached_path(video_id)
if output_path.exists():
return output_path
TRANSCODED_DIR.mkdir(exist_ok=True)
lock_file = _lock_path(video_id)
lock_fd = open(lock_file, "w")
try:
# 阻塞等待锁,最多等 10 分钟(转码大文件可能慢)
fcntl.flock(lock_fd, fcntl.LOCK_EX)
# 拿到锁后再检查一次:可能前面的进程已经转码完成
if output_path.exists():
return output_path
tmp_path = output_path.with_suffix(".mp4.tmp")
result = subprocess.run(
[
"ffmpeg", "-i", str(source_path),
"-c:v", "h264_videotoolbox", "-b:v", "1500k",
"-c:a", "aac",
"-movflags", "+faststart",
"-f", "mp4", # 输出文件名带.tmp后缀,ffmpeg无法从扩展名猜出格式,需显式指定
"-y", str(tmp_path),
],
capture_output=True, timeout=600,
)
if result.returncode != 0 or not tmp_path.exists():
tmp_path.unlink(missing_ok=True)
raise RuntimeError(result.stderr.decode("utf-8", errors="ignore"))
tmp_path.rename(output_path) # 转码完成后原子改名,避免并发请求读到半成品文件
return output_path
finally:
fcntl.flock(lock_fd, fcntl.LOCK_UN)
lock_fd.close()
lock_file.unlink(missing_ok=True)
def cache_stats():
if not TRANSCODED_DIR.exists():
return {"file_count": 0, "total_size_bytes": 0, "files": []}
files = []
total = 0
for f in TRANSCODED_DIR.glob("*.mp4"):
size = f.stat().st_size
total += size
files.append({"video_id": int(f.stem), "size_bytes": size})
return {"file_count": len(files), "total_size_bytes": total, "files": files}
def clear_cache():
if not TRANSCODED_DIR.exists():
return {"deleted": 0, "freed_bytes": 0}
deleted = 0
freed = 0
for f in TRANSCODED_DIR.glob("*.mp4"):
freed += f.stat().st_size
f.unlink()
deleted += 1
# 清理残留的 .tmp 和 .lock 文件
for f in TRANSCODED_DIR.glob("*.tmp"):
f.unlink(missing_ok=True)
for f in TRANSCODED_DIR.glob("*.lock"):
f.unlink(missing_ok=True)
return {"deleted": deleted, "freed_bytes": freed}