checkerboard op• Data kinds: none → table (an op determined by its arguments alone — it takes no image or data input)
• Call: import fullseye as fs; fs.ledger.sim_checkerboard(pattern_size, square_size, K, dist, pose, image_shape, supersample=3, margin=1.0, blur_sigma=0.0, noise_sigma=0.0, seed=0, black=0.1, white=0.9, background=0.5) (to call the implementation directly, import calib_lm; calib_lm.sim_checkerboard(pattern_size, square_size, K, dist, pose, image_shape, supersample=3, margin=1.0, blur_sigma=0.0, noise_sigma=0.0, seed=0, black=0.1, white=0.9, background=0.5); from the registry, opscalib.get("sim_checkerboard"))
• GPU: none (CPU reference implementation only)
Synthesizes a checkerboard image with known K, distortion and pose and returns it with the true pixel of every corner (table).
> The detailed description below is the original text — the summary and the headings are translated.
Render a checkerboard seen through a camera with known intrinsics K (3x3 or {fx, fy, cx, cy}), distortion dist ([k1, k2, p1, p2(, k3)], OpenCV order) and board pose pose (board -> camera 4x4), with the true pixel of every inner corner.
描画は投影の式とは逆向きの経路: 画素(supersample x supersample の標本)ごとに歪みを固定点反復で外し、視線を板の平面に当てて板の座標を求め、その色(黒・白・板の外の余白 margin マス分は白、その外は background)を塗って平均する。真の角は板の点を前向きに投影した値。だから検出の誤差は「描画の標本化 + 検出器」の誤差で、式の写しにはならない。blur_sigma(画素)でガウスぼけ、noise_sigma で正規雑音。
返す dict: image (H, W) [0, 1]、corners (N, 2) (row, col)、object_points (N, 2) (x, y)、visible(全部の角が画像の内側 2 画素以上にある)、pattern_size、square_size、K、dist、pose。
Raises ValueError: 引数の形・範囲(K が正でない、姿勢が剛体でない、板が背後にある、supersample が 1〜8 の外、色が [0, 1] の外)。
• camera_calibration family guide
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
• The canonical algorithm (author, year) and its uses are named in the family usage guide above.
• poc_calibration_truth_map — py -3.11 examples/poc_calibration_truth_map.py
table as input)image_points_to_world_plane · contour_to_world_plane_xld · sim_caltab · disp_caltab · calibration_error_map · calibration_uncertainty_map · calibration_next_pose
checkerboard)checkerboard_points · find_checkerboard_corners
*Provenance: calib_lm.py — CALIB operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.