tracking op• Data kinds: image2d → table
• Call: import fullseye as fs; fs.ledger.create_bg_esti(image, process_noise=0.0001, measurement_noise=0.001, threshold=0.1, foreground_gain=0.05) (to call the implementation directly, import mvtrack; mvtrack.create_bg_esti(image, process_noise=0.0001, measurement_noise=0.001, threshold=0.1, foreground_gain=0.05); from the registry, opsmv.get("create_bg_esti"))
• HALCON equivalent: create_bg_esti (the HALCON reference is a useful guide to its meaning and parameters)
• GPU: none (CPU reference implementation only)
Create a per-pixel Kalman background model from the first image.
> The detailed description below is the original text — the summary and the headings are translated.
各画素の背景はランダムウォークと見なし、過程の雑音 process_noise と観測の雑音 measurement_noise の分散からゲインが決まる。前景と判定された画素はゲインに foreground_gain を掛けて弱く更新し、通過する物体を背景に取り込まない。画素値は [0, 1] の float(threshold と雑音の分散も同じ尺度)。整数 dtype の画像と [0, 1] の外の値は ValueError(uint8 は / 255 してから渡す)。空の入力(image が 0 要素)は ValueError。
Args:
image: 最初の画像 (H, W)。
process_noise: 過程の雑音の分散(> 0)。
measurement_noise: 観測の雑音の分散(> 0)。
threshold: 前景と判定する残差の絶対値(> 0)。
foreground_gain: 前景の画素のゲイン倍率(0..1)。
Returns:
背景 background と分散 variance を持つモデルの dict。
• machine_vision_classics 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.
• machine_vision_tour — py -3.11 examples/machine_vision_tour.py
• poc_real_bg_kalman_tracking — py -3.11 examples/poc_real_bg_kalman_tracking.py
table as input)map_image · rectify_to_world_plane · change_radial_distortion_image · find_ncc_models · run_bg_esti · give_bg_esti · update_bg_esti · classify_class_gmm
tracking)filter_kalman · run_bg_esti · give_bg_esti · update_bg_esti
*Provenance: mvtrack.py — MV 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.