Initial scaffold: capture + vision modules with detect CLI

- capture/: frame sampling at configurable fps, ffmpeg audio extraction (WAV, whisper-ready)
- vision/: changed-pixel motion scoring, stable/moving segmentation, contour + perspective document detection, Laplacian sharpness scoring, optional CLAHE enhancement
- pipeline: two-pass detect (motion timeline, then best-frame crop per stable window) writing crops, debug frames, report.json, and motion_scores.csv
- CLI: probe / detect / extract-audio subcommands
- config.yaml with tunable thresholds; placeholder packages for events, transcribe, ocr, naming, pdf, review_cli
- synthetic sample video generator + 16 unit tests

paperpod/vision/enhance.py

@@ -0,0 +1,20 @@
+"""Optional image enhancement for OCR-readiness."""
+
+from __future__ import annotations
+
+import cv2
+import numpy as np
+
+
+def enhance_for_ocr(image_bgr: np.ndarray) -> np.ndarray:
+    """Boost local contrast (CLAHE on the luminance channel).
+
+    Deliberately conservative: no binarization, so the crop stays pleasant to
+    read in the PDF while giving OCR more to work with. Thresholding can be
+    added behind a config flag later if OCR needs it.
+    """
+    lab = cv2.cvtColor(image_bgr, cv2.COLOR_BGR2LAB)
+    l_chan, a_chan, b_chan = cv2.split(lab)
+    clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+    lab = cv2.merge((clahe.apply(l_chan), a_chan, b_chan))
+    return cv2.cvtColor(lab, cv2.COLOR_LAB2BGR)