rectify_to_world_plane — MV `resample` op

• Data kinds: image2d × table × matrix → image2d

• Call: import fullseye as fs; fs.ledger.rectify_to_world_plane(image, cam_par, pose, width, height, scale, origin=(0.0, 0.0), fill=0.0) (to call the implementation directly, import mvimage; mvimage.rectify_to_world_plane(image, cam_par, pose, width, height, scale, origin=(0.0, 0.0), fill=0.0); from the registry, opsmv.get("rectify_to_world_plane"))

• HALCON equivalent: image_to_world_plane (the HALCON reference is a useful guide to its meaning and parameters)

• GPU: none (CPU reference implementation only)

Usage

Rectify an image to a fronto-parallel view of the world plane z=0 (one pixel = scale world units).

> The detailed description below is the original text — the summary and the headings are translated.

世界の点 (x, y, 0) を pose(ワールド → カメラの 4x4)で写し、ピンホール投影と除算モデルの歪み(cam_par に kappa があるとき)を通して入力の座標を求める。出力の行は y、列は x に沿う。origin は出力の (0, 0) に当たる世界の (x, y)。カメラの後ろへ落ちる画素は fill。空の入力(image が 0 要素)は ValueError。

Args:

image: (H, W) の画像。

cam_par: fx / fy / cx / cy(と任意で kappa)の dict。

pose: 4x4 の同次変換(ワールド → カメラ)。

width: 出力の列数。

height: 出力の行数。

scale: 1 画素あたりのワールド単位(> 0)。

origin: 出力の左上の画素が指す世界の (x, y)。

fill: 入力の外とカメラの後ろの画素の値。

Returns:

(height, width) の float 画像。

出典: R. Hartley and A. Zisserman, Multiple View Geometry, 2nd ed., ch. 2 (平面の射影変換)。

Detailed usage guide

• machine_vision_classics family guide

References (sample data, literature)

• 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.

Runnable examples (verified samples that actually call this op)

• machine_vision_tour — py -3.11 examples/machine_vision_tour.py

• poc_real_chessboard_undistort — py -3.11 examples/poc_real_chessboard_undistort.py

Ops the type connects to (they accept `image2d` as input)

binocular_disparity_ms · binocular_distance_ms · reconstruct_surface_stereo · map_image · change_radial_distortion_image · crop_rectangle2 · atan2_image · area_center_gray

Same category (`resample`)

map_image · change_radial_distortion_image · crop_rectangle2

*Provenance: mvimage.py — MV operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

rectify_to_world_plane — MV resample op