Add video duration_s to inventory and propagate to merged TSV

build_video_inventory.py now opens each mp4 with cv2 to record
duration_s. Cached: a video already in the previous inventory keeps
its computed duration, so re-runs only pay the cv2 cost for new
recordings.

export_video_db_index.py looks up the matched video's duration and
writes it as training_video_duration_s / testing_video_duration_s
alongside the existing path columns. Useful for spotting unusually
short or long sessions and for sanity checks on the tracker output.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

scripts/build_video_inventory.py

@@ -64,6 +64,51 @@ def scan_videos(videos_root: Path) -> pd.DataFrame:
     return pd.DataFrame(rows)
 
 
+def video_duration_s(mp4_path: str) -> float | None:
+    """Read video duration in seconds via cv2. Returns None on failure."""
+    import cv2  # local import — heavy module, only needed when computing
+    cap = cv2.VideoCapture(mp4_path)
+    if not cap.isOpened():
+        return None
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    frames = cap.get(cv2.CAP_PROP_FRAME_COUNT)
+    cap.release()
+    if fps <= 0 or frames <= 0:
+        return None
+    return float(frames / fps)
+
+
+def add_durations(videos_df: pd.DataFrame, prev_inv_path: Path) -> pd.DataFrame:
+    """Annotate videos_df with a duration_s column.
+
+    Reuses durations from the previous inventory CSV when present
+    (keyed on mp4_path) — only newly-discovered videos pay the cv2 open cost.
+    """
+    cache: dict[str, float] = {}
+    if prev_inv_path.exists():
+        prev = pd.read_csv(prev_inv_path)
+        if "duration_s" in prev.columns:
+            for _, r in prev.dropna(subset=["duration_s"]).iterrows():
+                cache[r["mp4_path"]] = float(r["duration_s"])
+
+    durations: list[float | None] = []
+    todo_count = sum(1 for p in videos_df["mp4_path"] if p not in cache)
+    if todo_count:
+        print(f"  computing duration for {todo_count} new video(s)…")
+    try:
+        from tqdm.auto import tqdm
+    except ImportError:
+        def tqdm(it, **_): return it
+    for mp4_path in tqdm(videos_df["mp4_path"], desc="durations", unit="vid"):
+        if mp4_path in cache:
+            durations.append(cache[mp4_path])
+        else:
+            durations.append(video_duration_s(mp4_path))
+    videos_df = videos_df.copy()
+    videos_df["duration_s"] = durations
+    return videos_df
+
+
 def already_tracked_set(tracked_dir: Path) -> set[tuple[str, str]]:
     """Return the set of (date, time) sessions for which a tracking DB exists.
 
@@ -83,6 +128,8 @@ def main() -> None:
     videos_df = scan_videos(VIDEOS_ROOT)
     print(f"  found {len(videos_df)} video sessions on disk")
 
+    videos_df = add_durations(videos_df, INVENTORY_CSV)
+
     print(f"Loading metadata xlsx: {VIDEO_INFO_XLSX}")
     meta = pd.read_excel(VIDEO_INFO_XLSX)
     meta["session_date"] = meta["date"].dt.strftime("%Y-%m-%d")