a2e5214f03
铸渊 ICE-GL-ZY001 LL-172-20260707 冰朔委托: 新建第 5 子仓, 给苍耳(人类主控) + 鉴影(人格体) 专用 原 guanghulab/video-ai-system/ 东西太多(225 文件) · 找不到 · 乱 迁移: ⊢ 16 个核心 .hdlp (VA-GATE / VA-LIGHTHOUSE / VA-BROADCAST / VA-SYSTEM-STATUS 等) ⊢ 17 个子目录 (agents/engines/protocols/tasks/tools/assets/knowledge/memory/docs/config/brain/director-brain/experience/feedback/issues/plans/reference-analysis) 排除: ⊢ outputs/ (视频产物) ⊢ test-input/ test-output/ (测试) ⊢ data/ (临时数据) ⊢ preview-001/002 (旧产片) ⊢ 旧分镜/旧提示词/旧导演编码 后续: ⊢ 老仓 guanghulab/video-ai-system/ 改写为已迁出占位 ⊢ 苍耳+鉴影 写新东西进本仓 ⊢ GLOBAL-SEARCH 加 cang-ying 仓库 铸渊 ICE-GL-ZY001 · 2026-07-07 D167 冰朔 ICE-GL∞ 主权
599 lines
20 KiB
Python
599 lines
20 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
"""
|
||
SHOT-QC-AUTOMATION
|
||
镜头QC自动化 — 每个镜头自动拆帧，检查竖屏、字幕、换脸、牌匾、遮挡、现代物品。
|
||
|
||
功能:
|
||
1. 输入视频文件
|
||
2. 自动拆帧
|
||
3. 检查:
|
||
- 竖屏 (9:16)
|
||
- 字幕存在性和位置
|
||
- 换脸 (与参考图对比)
|
||
- 牌匾文字正确性
|
||
- 遮挡 (人物被遮挡)
|
||
- 现代物品 (手机、汽车等)
|
||
4. 输出 QC 报告 JSON
|
||
|
||
依赖:
|
||
pip install opencv-python numpy # 基础
|
||
pip install pytesseract # OCR (需要系统安装 tesseract)
|
||
# YOLO 可选: pip install ultralytics
|
||
|
||
用法:
|
||
python shot-qc-automation.py --video input.mp4 --character CHAR-003-SuBai
|
||
python shot-qc-automation.py --batch video_list.json
|
||
python shot-qc-automation.py --video input.mp4 --output qc_report.json
|
||
"""
|
||
|
||
import os
|
||
import sys
|
||
import json
|
||
import argparse
|
||
from pathlib import Path
|
||
from datetime import datetime
|
||
import numpy as np
|
||
|
||
try:
|
||
import cv2
|
||
CV2_AVAILABLE = True
|
||
except ImportError:
|
||
CV2_AVAILABLE = False
|
||
print("⚠️ OpenCV (cv2) 未安装，将使用简化模式")
|
||
|
||
try:
|
||
import pytesseract
|
||
TESSERACT_AVAILABLE = True
|
||
except ImportError:
|
||
TESSERACT_AVAILABLE = False
|
||
print("⚠️ pytesseract 未安装，OCR 功能不可用")
|
||
|
||
try:
|
||
from PIL import Image
|
||
PIL_AVAILABLE = True
|
||
except ImportError:
|
||
PIL_AVAILABLE = False
|
||
|
||
|
||
PROJECT_ROOT = Path(__file__).parent.parent
|
||
sys.path.insert(0, str(PROJECT_ROOT / "engines"))
|
||
|
||
|
||
class ShotQCAutomation:
|
||
"""镜头QC自动化"""
|
||
|
||
def __init__(self, character_id=None, reference_images=None):
|
||
self.character_id = character_id
|
||
self.reference_images = reference_images or []
|
||
self.qc_items = [
|
||
"vertical_screen", # 竖屏
|
||
"subtitle", # 字幕
|
||
"face_swap", # 换脸
|
||
"plaque_text", # 牌匾文字
|
||
"occlusion", # 遮挡
|
||
"modern_items" # 现代物品
|
||
]
|
||
|
||
# 加载参考图
|
||
self.reference_images_data = []
|
||
if character_id:
|
||
self._load_reference_images()
|
||
|
||
def _load_reference_images(self):
|
||
"""加载角色参考图"""
|
||
if not CV2_AVAILABLE:
|
||
return
|
||
|
||
char_dir = PROJECT_ROOT / "assets" / "characters" / self.character_id / "approved"
|
||
if not char_dir.exists():
|
||
print(f"⚠️ 角色目录不存在: {char_dir}")
|
||
return
|
||
|
||
for img_file in char_dir.glob("*.png"):
|
||
img = cv2.imread(str(img_file))
|
||
if img is not None:
|
||
self.reference_images_data.append({
|
||
"path": str(img_file),
|
||
"data": img,
|
||
"name": img_file.name
|
||
})
|
||
print(f" ✓ 已加载参考图: {img_file.name}")
|
||
|
||
print(f" 共加载 {len(self.reference_images_data)} 张参考图")
|
||
|
||
def qc_video(self, video_path, output_path=None):
|
||
"""
|
||
QC 单个视频
|
||
|
||
返回:
|
||
{
|
||
"video_path": str,
|
||
"passed": bool,
|
||
"score": float, # 0-10
|
||
"checks": {
|
||
"vertical_screen": {"passed": bool, "detail": str},
|
||
"subtitle": {...},
|
||
...
|
||
},
|
||
"frames_checked": int,
|
||
"issues": list
|
||
}
|
||
"""
|
||
print(f"\n🔍 QC 视频: {Path(video_path).name}")
|
||
print("=" * 60)
|
||
|
||
video_path = Path(video_path)
|
||
if not video_path.exists():
|
||
return {"passed": False, "error": f"视频不存在: {video_path}"}
|
||
|
||
if not CV2_AVAILABLE:
|
||
print("⚠️ OpenCV 不可用，跳过 QC")
|
||
return {
|
||
"passed": None,
|
||
"warning": "OpenCV 不可用，QC 未执行",
|
||
"qc_skipped": True
|
||
}
|
||
|
||
# 打开视频
|
||
cap = cv2.VideoCapture(str(video_path))
|
||
if not cap.isOpened():
|
||
return {"passed": False, "error": f"无法打开视频: {video_path}"}
|
||
|
||
# 视频信息
|
||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
||
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
||
|
||
print(f" 分辨率: {width}x{height}")
|
||
print(f" FPS: {fps}")
|
||
print(f" 帧数: {frame_count}")
|
||
|
||
# 检查项
|
||
results = {
|
||
"video_path": str(video_path),
|
||
"resolution": f"{width}x{height}",
|
||
"fps": fps,
|
||
"frame_count": frame_count,
|
||
"passed": True,
|
||
"score": 10.0,
|
||
"checks": {},
|
||
"frames_checked": 0,
|
||
"issues": []
|
||
}
|
||
|
||
# 1. 竖屏检查
|
||
print(f"\n [1/6] 竖屏检查...")
|
||
vertical_result = self._check_vertical_screen(width, height)
|
||
results["checks"]["vertical_screen"] = vertical_result
|
||
if not vertical_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 2.0
|
||
results["issues"].append("竖屏比例错误")
|
||
|
||
# 2. 字幕检查 (抽帧)
|
||
print(f" [2/6] 字幕检查...")
|
||
subtitle_result = self._check_subtitle(cap, frame_count, fps)
|
||
results["checks"]["subtitle"] = subtitle_result
|
||
if not subtitle_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 1.5
|
||
results["issues"].append("字幕检查失败")
|
||
|
||
# 3. 换脸检查 (与参考图对比)
|
||
print(f" [3/6] 换脸检查...")
|
||
face_swap_result = self._check_face_swap(cap, frame_count, fps)
|
||
results["checks"]["face_swap"] = face_swap_result
|
||
if not face_swap_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 2.0
|
||
results["issues"].append("疑似换脸")
|
||
|
||
# 4. 牌匾文字检查
|
||
print(f" [4/6] 牌匾文字检查...")
|
||
plaque_result = self._check_plaque_text(cap, frame_count, fps)
|
||
results["checks"]["plaque_text"] = plaque_result
|
||
if not plaque_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 1.5
|
||
results["issues"].append("牌匾文字错误")
|
||
|
||
# 5. 遮挡检查
|
||
print(f" [5/6] 遮挡检查...")
|
||
occlusion_result = self._check_occlusion(cap, frame_count, fps)
|
||
results["checks"]["occlusion"] = occlusion_result
|
||
if not occlusion_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 1.0
|
||
results["issues"].append("人物被遮挡")
|
||
|
||
# 6. 现代物品检查
|
||
print(f" [6/6] 现代物品检查...")
|
||
modern_result = self._check_modern_items(cap, frame_count, fps)
|
||
results["checks"]["modern_items"] = modern_result
|
||
if not modern_result["passed"]:
|
||
results["passed"] = False
|
||
results["score"] -= 1.0
|
||
results["issues"].append("检测到现代物品")
|
||
|
||
# 确保分数在 0-10 之间
|
||
results["score"] = max(0, min(10, results["score"]))
|
||
|
||
# 重置视频到开头
|
||
cap.set(cv2.CAP_PROP_POS_FRAMES, 0)
|
||
cap.release()
|
||
|
||
# 打印总结
|
||
print(f"\n📊 QC 总结")
|
||
print(f" 通过: {'✅' if results['passed'] else '❌'}")
|
||
print(f" 分数: {results['score']:.1f}/10")
|
||
print(f" 问题数: {len(results['issues'])}")
|
||
for issue in results["issues"]:
|
||
print(f" - {issue}")
|
||
|
||
# 保存报告
|
||
if output_path is None:
|
||
output_path = PROJECT_ROOT / "outputs" / "qc_reports" / f"{video_path.stem}_qc.json"
|
||
else:
|
||
output_path = Path(output_path)
|
||
|
||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||
with open(output_path, "w", encoding="utf-8") as f:
|
||
json.dump(results, f, ensure_ascii=False, indent=2)
|
||
|
||
print(f"\n 报告已保存: {output_path}")
|
||
|
||
return results
|
||
|
||
def _check_vertical_screen(self, width, height):
|
||
"""检查竖屏 (9:16)"""
|
||
# 竖屏: 宽度 < 高度，比例接近 9:16
|
||
if width >= height:
|
||
return {
|
||
"passed": False,
|
||
"detail": f"横屏 {width}x{height}，应为竖屏 9:16",
|
||
"aspect_ratio": width / height
|
||
}
|
||
|
||
# 检查比例是否接近 9:16
|
||
ratio = width / height
|
||
target_ratio = 9 / 16 # ≈ 0.5625
|
||
|
||
if abs(ratio - target_ratio) < 0.05:
|
||
return {
|
||
"passed": True,
|
||
"detail": f"竖屏比例正确 {width}x{height} (ratio={ratio:.3f})",
|
||
"aspect_ratio": ratio
|
||
}
|
||
else:
|
||
return {
|
||
"passed": False,
|
||
"detail": f"竖屏比例不正确 {width}x{height} (ratio={ratio:.3f}, target={target_ratio:.3f})",
|
||
"aspect_ratio": ratio
|
||
}
|
||
|
||
def _check_subtitle(self, cap, frame_count, fps):
|
||
"""检查字幕 (抽帧 + OCR)"""
|
||
if not TESSERACT_AVAILABLE:
|
||
return {
|
||
"passed": True, # 无法检查，默认通过
|
||
"detail": "Tesseract OCR 不可用，跳过字幕检查",
|
||
"skipped": True
|
||
}
|
||
|
||
# 抽帧: 每秒抽1帧
|
||
sample_interval = int(fps)
|
||
if sample_interval < 1:
|
||
sample_interval = 1
|
||
|
||
frames_to_check = []
|
||
for i in range(0, frame_count, sample_interval):
|
||
frames_to_check.append(i)
|
||
|
||
# 限制最多检查 30 帧
|
||
if len(frames_to_check) > 30:
|
||
step = len(frames_to_check) // 30
|
||
frames_to_check = frames_to_check[::step][:30]
|
||
|
||
subtitle_found = False
|
||
subtitle_positions = []
|
||
|
||
for frame_idx in frames_to_check:
|
||
cap.set(cv2.CAP_PROP_POS_FRAMES, frame_idx)
|
||
ret, frame = cap.read()
|
||
if not ret:
|
||
continue
|
||
|
||
# OCR 检测字幕 (通常在画面底部 1/4 区域)
|
||
height, width = frame.shape[:2]
|
||
subtitle_region = frame[int(height * 0.75):, :] # 底部 1/4
|
||
|
||
try:
|
||
text = pytesseract.image_to_string(subtitle_region, config='--psm 6')
|
||
if text.strip():
|
||
subtitle_found = True
|
||
subtitle_positions.append(frame_idx / fps) # 秒数
|
||
except Exception as e:
|
||
pass
|
||
|
||
if subtitle_found:
|
||
return {
|
||
"passed": True,
|
||
"detail": f"检测到字幕，出现位置: {len(subtitle_positions)} 处",
|
||
"subtitle_positions": subtitle_positions[:10] # 前10个位置
|
||
}
|
||
else:
|
||
return {
|
||
"passed": False,
|
||
"detail": "未检测到字幕",
|
||
"subtitle_positions": []
|
||
}
|
||
|
||
def _check_face_swap(self, cap, frame_count, fps):
|
||
"""检查换脸 (与参考图对比)"""
|
||
if len(self.reference_images_data) == 0:
|
||
return {
|
||
"passed": True, # 无参考图，无法检查
|
||
"detail": "无参考图，跳过换脸检查",
|
||
"skipped": True
|
||
}
|
||
|
||
# 抽帧: 每分钟抽1帧
|
||
sample_interval = int(fps * 60)
|
||
if sample_interval < 1:
|
||
sample_interval = 1
|
||
|
||
frames_to_check = []
|
||
for i in range(0, frame_count, sample_interval):
|
||
frames_to_check.append(i)
|
||
|
||
# 限制最多检查 10 帧
|
||
if len(frames_to_check) > 10:
|
||
step = len(frames_to_check) // 10
|
||
frames_to_check = frames_to_check[::step][:10]
|
||
|
||
face_swap_detected = False
|
||
suspicious_frames = []
|
||
|
||
for frame_idx in frames_to_check:
|
||
cap.set(cv2.CAP_PROP_POS_FRAMES, frame_idx)
|
||
ret, frame = cap.read()
|
||
if not ret:
|
||
continue
|
||
|
||
# 简化方法: 比较直方图
|
||
frame_hist = cv2.calcHist([frame], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256])
|
||
cv2.normalize(frame_hist, frame_hist)
|
||
|
||
for ref in self.reference_images_data:
|
||
ref_hist = cv2.calcHist([ref["data"]], [0, 1, 2], None, [8, 8, 8], [0, 256, 0, 256, 0, 256])
|
||
cv2.normalize(ref_hist, ref_hist)
|
||
|
||
# 比较直方图相关性
|
||
similarity = cv2.compareHist(frame_hist, ref_hist, cv2.HISTCMP_CORREL)
|
||
|
||
if similarity < 0.3: # 低相似度 = 可能换脸
|
||
face_swap_detected = True
|
||
suspicious_frames.append({
|
||
"frame": frame_idx,
|
||
"time": frame_idx / fps,
|
||
"similarity": float(similarity)
|
||
})
|
||
|
||
if not face_swap_detected:
|
||
return {
|
||
"passed": True,
|
||
"detail": f"未检测到换脸 (检查了 {len(frames_to_check)} 帧)",
|
||
"frames_checked": len(frames_to_check)
|
||
}
|
||
else:
|
||
return {
|
||
"passed": False,
|
||
"detail": f"疑似换脸 (检测到 {len(suspicious_frames)} 处异常)",
|
||
"suspicious_frames": suspicious_frames[:5]
|
||
}
|
||
|
||
def _check_plaque_text(self, cap, frame_count, fps):
|
||
"""检查牌匾文字 (OCR)"""
|
||
if not TESSERACT_AVAILABLE:
|
||
return {
|
||
"passed": True,
|
||
"detail": "Tesseract OCR 不可用，跳过牌匾文字检查",
|
||
"skipped": True
|
||
}
|
||
|
||
# 抽帧: 牌匾通常静止，抽 5 帧即可
|
||
frames_to_check = [0, int(frame_count * 0.25), int(frame_count * 0.5), int(frame_count * 0.75), frame_count - 1]
|
||
frames_to_check = [f for f in frames_to_check if f < frame_count]
|
||
|
||
plaque_text_detected = []
|
||
correct_text = "天道宗" # 期望的牌匾文字
|
||
|
||
for frame_idx in frames_to_check:
|
||
cap.set(cv2.CAP_PROP_POS_FRAMES, frame_idx)
|
||
ret, frame = cap.read()
|
||
if not ret:
|
||
continue
|
||
|
||
# OCR 整帧
|
||
try:
|
||
text = pytesseract.image_to_string(frame, config='--psm 6')
|
||
if correct_text in text:
|
||
plaque_text_detected.append({
|
||
"frame": frame_idx,
|
||
"time": frame_idx / fps,
|
||
"text": text.strip()[:50]
|
||
})
|
||
except Exception as e:
|
||
pass
|
||
|
||
if len(plaque_text_detected) > 0:
|
||
return {
|
||
"passed": True,
|
||
"detail": f"牌匾文字正确 '{correct_text}' (在 {len(plaque_text_detected)} 帧中检测到)",
|
||
"detected": plaque_text_detected
|
||
}
|
||
else:
|
||
return {
|
||
"passed": False,
|
||
"detail": f"未检测到牌匾文字 '{correct_text}'",
|
||
"warning": "可能牌匾文字错误或未出现在画面中"
|
||
}
|
||
|
||
def _check_occlusion(self, cap, frame_count, fps):
|
||
"""检查遮挡 (人物被遮挡)"""
|
||
# 简化方法: 检测画面中是否突然出现大块纯色区域 (可能是水印或遮挡)
|
||
|
||
sample_interval = int(fps * 10) # 每10秒抽1帧
|
||
if sample_interval < 1:
|
||
sample_interval = 1
|
||
|
||
frames_to_check = []
|
||
for i in range(0, frame_count, sample_interval):
|
||
frames_to_check.append(i)
|
||
|
||
occlusion_detected = False
|
||
|
||
for frame_idx in frames_to_check:
|
||
cap.set(cv2.CAP_PROP_POS_FRAMES, frame_idx)
|
||
ret, frame = cap.read()
|
||
if not ret:
|
||
continue
|
||
|
||
# 转灰度
|
||
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
||
|
||
# 计算灰度直方图
|
||
hist = cv2.calcHist([gray], [0], None, [256], [0, 256])
|
||
hist = hist.flatten()
|
||
|
||
# 如果某个灰度值占比过高 = 可能有遮挡/水印
|
||
max_ratio = np.max(hist) / (frame.shape[0] * frame.shape[1])
|
||
if max_ratio > 0.3: # 30% 以上像素是同一颜色
|
||
occlusion_detected = True
|
||
break
|
||
|
||
if not occlusion_detected:
|
||
return {
|
||
"passed": True,
|
||
"detail": f"未检测到明显遮挡 (检查了 {len(frames_to_check)} 帧)"
|
||
}
|
||
else:
|
||
return {
|
||
"passed": False,
|
||
"detail": "检测到可能的遮挡 (画面中有大块纯色区域)"
|
||
}
|
||
|
||
def _check_modern_items(self, cap, frame_count, fps):
|
||
"""检查现代物品 (手机、汽车等)"""
|
||
# 简化方法: 检测画面中是否有现代物品的特征颜色/形状
|
||
|
||
# TODO: 使用 YOLO 检测现代物品
|
||
# 暂时跳过，返回通过
|
||
|
||
return {
|
||
"passed": True,
|
||
"detail": "现代物品检查 (TODO: 需要 YOLO 模型)",
|
||
"skipped": True,
|
||
"todo": "Implement YOLO-based modern item detection"
|
||
}
|
||
|
||
def batch_qc(self, video_list_config):
|
||
"""
|
||
批量 QC
|
||
|
||
video_list_config 格式:
|
||
{
|
||
"videos": [
|
||
{"path": "ep01-shot01.mp4", "character": "CHAR-003-SuBai"},
|
||
...
|
||
]
|
||
}
|
||
"""
|
||
if isinstance(video_list_config, str):
|
||
config_file = Path(video_list_config)
|
||
with open(config_file, "r", encoding="utf-8") as f:
|
||
config = json.load(f)
|
||
videos = config.get("videos", [])
|
||
elif isinstance(video_list_config, list):
|
||
videos = video_list_config
|
||
else:
|
||
videos = []
|
||
|
||
print(f"\n📦 批量 QC: {len(videos)} 个视频")
|
||
|
||
results = []
|
||
for i, video_config in enumerate(videos):
|
||
print(f"\n 进度: [{i+1}/{len(videos)}]")
|
||
|
||
video_path = video_config.get("path")
|
||
character_id = video_config.get("character", self.character_id)
|
||
|
||
qc = ShotQCAutomation(character_id=character_id)
|
||
result = qc.qc_video(video_path)
|
||
results.append(result)
|
||
|
||
# 统计
|
||
passed_count = sum(1 for r in results if r.get("passed"))
|
||
print(f"\n✅ 批量 QC 完成: {passed_count}/{len(results)} 通过")
|
||
|
||
# 保存批量报告
|
||
report_path = PROJECT_ROOT / "outputs" / "qc_reports" / f"batch_qc_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
|
||
report_path.parent.mkdir(parents=True, exist_ok=True)
|
||
|
||
with open(report_path, "w", encoding="utf-8") as f:
|
||
json.dump({
|
||
"total": len(results),
|
||
"passed": passed_count,
|
||
"results": results,
|
||
"generated_at": datetime.now().isoformat()
|
||
}, f, ensure_ascii=False, indent=2)
|
||
|
||
print(f" 报告已保存: {report_path}")
|
||
|
||
return results
|
||
|
||
|
||
def main():
|
||
parser = argparse.ArgumentParser(description="SHOT-QC-AUTOMATION")
|
||
parser.add_argument("--video", type=str, help="输入视频路径")
|
||
parser.add_argument("--character", type=str, help="角色ID (用于换脸检查)")
|
||
parser.add_argument("--output", type=str, help="输出 QC 报告路径")
|
||
parser.add_argument("--batch", type=str, help="批量 QC 配置文件 (JSON)")
|
||
|
||
args = parser.parse_args()
|
||
|
||
if args.batch:
|
||
# 批量模式
|
||
qc = ShotQCAutomation(character_id=args.character)
|
||
results = qc.batch_qc(args.batch)
|
||
sys.exit(0 if all(r.get("passed") for r in results) else 1)
|
||
|
||
if not args.video:
|
||
parser.print_help()
|
||
sys.exit(1)
|
||
|
||
# 单文件模式
|
||
qc = ShotQCAutomation(character_id=args.character)
|
||
result = qc.qc_video(args.video, output_path=args.output)
|
||
|
||
if result.get("passed"):
|
||
print(f"\n✅ QC 通过")
|
||
sys.exit(0)
|
||
elif result.get("passed") is None and result.get("qc_skipped"):
|
||
print(f"\n⚠️ QC 跳过 (依赖不可用)")
|
||
sys.exit(0)
|
||
else:
|
||
if result.get("error"):
|
||
print(f"\n❌ QC 失败: {result['error']}")
|
||
else:
|
||
issues = result.get("issues") or []
|
||
issue_text = "；".join(issues) if issues else "未通过阈值"
|
||
print(f"\n❌ QC 未通过: {issue_text}")
|
||
sys.exit(1)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|