Fix smart_detect: correct pos index, remove O(n²) loop, clean up

- actual_pos_s[] tracks real timestamps per frame (was using positions[i]
  which breaks when frames fail to read)
- Replace O(n²) np.array_equal logo frame matching with simple bool list
- Remove unused pos_set variable
- Fix docstring still mentioning '8s tail' after removing it
- All variables consistent: logo_gray_frames replaces logo_frames_gray

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

backend/tools/smart_detect.py

@@ -15,92 +15,68 @@ def detect_static_regions(video_path: str, sample_frames: int = 30, threshold: f
                           max_scan_seconds: float = None):
     """
     饱和度签名 + 跨帧对比法检测水印/Logo。
-    采样策略：每秒采一帧（顺序读取，不随机 seek）+ 超长视频后段每8秒一帧。
-    分析时缩放到 1/4 分辨率提速，结果坐标还原到原始尺寸。
+    采样策略：全程每秒一帧，分析时缩放到 1/4 分辨率提速，坐标还原回原始尺寸。
     """
     cap = cv2.VideoCapture(video_path)
     total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
     fps = cap.get(cv2.CAP_PROP_FPS) or 30.0
-    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    orig_frame_w, orig_frame_h = w, h   # 保存原始分辨率，用于最终坐标还原
+    orig_frame_w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    orig_frame_h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
     duration_s = total / fps
 
-    # ── 采样策略：全程每秒采一帧 ─────────────────────────────────────────
+    # 全程每秒采一帧
     step = max(1, int(fps))
     positions = list(range(0, total, step))
 
-    # ── 顺序读取，缩放到 1/4 分辨率加速分析 ────────────────────────────────
-    SW, SH = max(1, w // 4), max(1, h // 4)   # 分析用小尺寸
-    pos_set = set(positions)
-    bgr_frames_small = []    # 缩放后的小帧（用于分析）
-    bgr_frames_orig  = []    # 原始尺寸帧（用于 SAM2，只保留少数几帧）
+    # 分析用 1/4 分辨率加速
+    SW, SH = max(1, orig_frame_w // 4), max(1, orig_frame_h // 4)
+
+    bgr_frames = []    # 小尺寸帧，用于分析
     gray_frames = []
-    keep_orig_interval = max(1, len(positions) // 8)   # 每隔若干帧保留一张原始尺寸
-
-    cap.set(cv2.CAP_PROP_POS_FRAMES, 0)
-    frame_idx = 0
-    pos_iter = iter(sorted(positions))
-    next_pos = next(pos_iter, None)
-
-    while next_pos is not None:
-        if frame_idx < next_pos:
-            # 快速跳帧：只有在需要的位置才真正读
-            cap.set(cv2.CAP_PROP_POS_FRAMES, next_pos)
-            frame_idx = next_pos
+    actual_pos_s = []  # 每帧对应的时间戳（秒）
 
+    for pos in positions:
+        cap.set(cv2.CAP_PROP_POS_FRAMES, pos)
         ret, frame = cap.read()
         if not ret:
-            next_pos = next(pos_iter, None)
             continue
-
         small = cv2.resize(frame, (SW, SH), interpolation=cv2.INTER_AREA)
-        bgr_frames_small.append(small)
+        bgr_frames.append(small)
         gray_frames.append(cv2.cvtColor(small, cv2.COLOR_BGR2GRAY).astype(np.float32))
-        if len(bgr_frames_orig) == 0 or len(bgr_frames_small) % keep_orig_interval == 0:
-            bgr_frames_orig.append(frame)
-
-        frame_idx += 1
-        next_pos = next(pos_iter, None)
+        actual_pos_s.append(pos / fps)
 
     cap.release()
 
-    # 后续分析全部用小尺寸帧
-    bgr_frames = bgr_frames_small
-    w, h = SW, SH   # 分析坐标空间切换到小尺寸
-
     print(f"[SAM2-detect] 采样 {len(bgr_frames)} 帧（全程每秒一帧，共{duration_s:.1f}s，分析尺寸{SW}x{SH}）", flush=True)
 
     if len(bgr_frames) < 4:
         print(f"[SAM2-detect] 帧数不足4帧，返回空", flush=True)
         return []
 
-    # ── 阶段1：通过高饱和度识别含logo帧 ──────────────────────────────────
-    # 水印/logo通常色彩比视频自然内容更鲜艳（高饱和度）
-    # 在帧的上半部分（logo常出现区域）检测高饱和度像素数
-    top_h = h // 5  # 检查帧顶部 20%
-    logo_sat_thresh = 200   # 饱和度 > 200 认为是logo颜色
-    logo_min_pixels = top_h * w * 0.003  # 至少 0.3% 的上方区域为logo颜色
+    # ── 阶段1：高饱和度识别含logo帧 ─────────────────────────────────────
+    top_h = SH // 5
+    logo_sat_thresh = 200
+    logo_min_pixels = top_h * SW * 0.003
 
-    logo_frames_gray = []
-    for i, (bgr, gray) in enumerate(zip(bgr_frames, gray_frames)):
+    is_logo = []
+    for i, bgr in enumerate(bgr_frames):
         hsv = cv2.cvtColor(bgr, cv2.COLOR_BGR2HSV)
         high_sat = int(np.sum(hsv[:top_h, :, 1] > logo_sat_thresh))
-        pos_s = positions[i] / fps
-        if high_sat >= logo_min_pixels:
-            logo_frames_gray.append(gray)
-            print(f"[SAM2-detect]   ✓ {pos_s:.1f}s: 高饱和={high_sat}px (含logo)", flush=True)
-        else:
-            print(f"[SAM2-detect]   ✗ {pos_s:.1f}s: 高饱和={high_sat}px (无logo)", flush=True)
+        has_logo = high_sat >= logo_min_pixels
+        is_logo.append(has_logo)
+        mark = '✓' if has_logo else '✗'
+        print(f"[SAM2-detect]   {mark} {actual_pos_s[i]:.1f}s: 高饱和={high_sat}px", flush=True)
 
-    print(f"[SAM2-detect] logo含帧: {len(logo_frames_gray)}/{len(bgr_frames)}", flush=True)
+    logo_bgr_frames  = [bgr_frames[i] for i, v in enumerate(is_logo) if v]
+    nlogo_bgr_frames = [bgr_frames[i] for i, v in enumerate(is_logo) if not v]
+    logo_gray_frames = [gray_frames[i] for i, v in enumerate(is_logo) if v]
 
-    logo_bgr_frames = [bgr_frames[i] for i, g in enumerate(gray_frames)
-                       if any(np.array_equal(g, l) for l in logo_frames_gray)]
-    nlogo_bgr_frames = [bgr_frames[i] for i, g in enumerate(gray_frames)
-                        if not any(np.array_equal(g, l) for l in logo_frames_gray)]
+    print(f"[SAM2-detect] logo含帧: {len(logo_bgr_frames)}/{len(bgr_frames)}", flush=True)
 
-    if len(logo_frames_gray) < 2:
+    # 分析时使用小尺寸坐标空间
+    w, h = SW, SH
+
+    if len(logo_gray_frames) < 2:
         print(f"[SAM2-detect] logo帧不足，回退到时序std法", flush=True)
         stack = np.stack(gray_frames, axis=0)
         std_map = np.std(stack, axis=0)