Files
myscan/tools/scan.py
T
erikandClaude Opus 5.5 026aa6c894 Global page assembly with loop closures and lens undistortion
The frame-by-frame stitcher accumulated drift, so later passes landed rotated
and offset, doubling text. myscan/pagegraph.py instead solves all frame poses
together: ECC odometry between consecutive frames (bridging single corrupt
frames), SIFT+RANSAC loop closures between overlapping passes, and a robust
Gauss-Newton pose graph. Loop matches must agree over the whole overlap, which
rejects matches on repeated text. Off-page frames and frames that disagree
with the mosaic are left out of the render.

calib.Undistort applies the EEPROM lens model (OpenCV k1..k3, p1, p2 plus
the tilt homography, as decoded in EEPROM.md); up to 8.8 px at the corners.

scan.py registers frames on a worker thread so capture no longer drops
frames, then assembles the page after the stop press (~11 s for a full
page). stitch.py uses the new assembly by default; --live keeps the old one.

EEPROM.md documents the full calibration blob layout, checksum and signature.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-02 13:06:45 +00:00

140 lines
5.7 KiB
Python

#!/usr/bin/env python3
"""Scan with the scan button, like the original app: press it to start, glide the
mouse over the page, press it again to stop. Frames are registered while you scan;
after the stop press the page is assembled from all of them at once (see
myscan/pagegraph.py) and saved as <outdir>/scan-YYYYmmdd-HHMMSS.png. The mouse goes
back to mouse mode between scans (and on Ctrl-C)."""
import argparse
import csv
import os
import queue
import sys
import threading
import time
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
from myscan.session import ScanSession, quiet_libjpeg # noqa: E402
quiet_libjpeg()
import cv2 # noqa: E402
from myscan import calib # noqa: E402
from myscan.pagegraph import PageGraph # noqa: E402
from myscan.xu import XU # noqa: E402
def wait_press(x, poll=0.05):
"""Block until the scan button goes down then up again."""
prev = 1
while True:
b = x.scan_button()
if b and not prev:
break
prev = b
time.sleep(poll)
while x.scan_button():
time.sleep(poll)
def scan_page(x, a, frames_dir=None, flat=None, undistort=None, gains=None):
"""Capture until the button is pressed again. Frames are registered (and saved) on a
worker thread so capture never waits; returns the PageGraph, or None."""
g, rows, work = None, [], queue.Queue()
def worker():
while (item := work.get()) is not None:
n, im, v = item
g.add(im, v)
if frames_dir:
cv2.imwrite(os.path.join(frames_dir, f"f{n:05d}.png"), im)
th = None
with ScanSession(a.video, a.target, a.exposure, xu=x, gains=gains) as s:
down, last = 0, 0.0
for t, n, im, rec in s.frames(color=not a.gray):
if g is None:
g = PageGraph(im.shape, flat=flat, undistort=undistort)
th = threading.Thread(target=worker, daemon=True)
th.start()
work.put((n, im, rec.v))
if frames_dir:
rows.append([round(t, 4), n, rec.counter, *rec.v, rec.b14, rec.b15, rec.b16, rec.flags, s.e6,
round(float(im.mean()), 1), rec.raw.hex()])
# Stop on a press: two "down" reads in a row (debounce), ignoring the first
# 0.7 s so a bouncing start press can't end the scan.
if n % 2 == 0:
down = down + 1 if x.scan_button() else 0
if down >= 2 and t > 0.7:
break
if t >= a.max_time:
print("max scan time reached", flush=True)
break
if t - last >= 1:
print(f"\r {t:5.1f}s {n + 1} frames ({g.n} registered) E6={s.e6}", end="", flush=True)
last = t
print()
if th:
work.put(None)
th.join()
if frames_dir: # same layout as tools/record.py, so tools/stitch.py can replay it
with open(os.path.join(frames_dir, "records.csv"), "w", newline="") as fh:
w = csv.writer(fh)
w.writerow(["t", "frame", "counter", "v0", "v1", "v2", "v3", "v4", "v5",
"b14", "b15", "b16", "flags", "e6", "brightness", "raw"])
w.writerows(rows)
return g
def main():
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--outdir", default="scans")
ap.add_argument("--once", action="store_true", help="exit after one page")
ap.add_argument("--now", action="store_true", help="start the first scan immediately")
ap.add_argument("--video", default="/dev/video4")
ap.add_argument("--target", type=float, default=200, help="auto-exposure target for paper (95th pct of brightest channel)")
ap.add_argument("--exposure", type=int, help="fixed E6 value instead of auto-exposure")
ap.add_argument("--gray", action="store_true")
ap.add_argument("--no-wb", action="store_true", help="skip white-patch balancing")
ap.add_argument("--no-flat", action="store_true", help="skip the EEPROM flat-field correction")
ap.add_argument("--no-undistort", action="store_true", help="skip the EEPROM lens correction")
ap.add_argument("--save-frames", action="store_true", help="also keep raw frames + records.csv per scan")
ap.add_argument("--max-time", type=float, default=180, help="stop a scan after this many seconds")
a = ap.parse_args()
os.makedirs(a.outdir, exist_ok=True)
x = XU(a.video)
print("reading calibration from the mouse's EEPROM (cached after the first time)", flush=True)
cal = calib.load(x)
flat = None if a.no_flat else calib.FlatField(cal)
undistort = None if a.no_undistort else calib.Undistort(cal)
gains = cal["gains_rgb"]
first = True
try:
while True:
if not (first and a.now):
print("press the scan button to start (Ctrl-C to quit)", flush=True)
wait_press(x)
first = False
print("scanning - press the scan button again to stop", flush=True)
name = time.strftime("scan-%Y%m%d-%H%M%S")
frames_dir = os.path.join(a.outdir, name) if a.save_frames else None
if frames_dir:
os.makedirs(frames_dir)
g = scan_page(x, a, frames_dir, flat, undistort, gains)
if g is None or g.n < 2:
print("no frames captured")
else:
print("assembling the page...", flush=True)
t0 = time.time()
page = g.image(white_balance=not a.no_wb)
path = os.path.join(a.outdir, name + ".png")
cv2.imwrite(path, page)
print(f"saved {path} ({time.time() - t0:.1f} s; {g.stats})", flush=True)
if a.once:
break
except KeyboardInterrupt:
print("\nbye")
if __name__ == "__main__":
main()