Metraipolis › archive › dc_2116dcaaba91

HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation — arXiv:2609.21597

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.21597
License (as archived): CC0-1.0
Archived: 2026-10-10T02:29:38.016Z
SHA-256 of the archived text: 92e87e8f32fc7bcf3987b22d9b6e39ca2f4c2d5b3c1c5093fb7ef14d949cd519
Stable URL of this page: https://metraipolis.com/documento/dc_2116dcaaba91

How to cite

HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation — arXiv:2609.21597 — arXiv (en), https://arxiv.org/abs/2609.21597 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2116dcaaba91 (Metraipolis archive dc_2116dcaaba91, sha256 92e87e8f32fc7bcf3987b22d9b6e39ca2f4c2d5b3c1c5093fb7ef14d949cd519)

BibTeX

@misc{dc2116dcaaba91,
  title = {HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation — arXiv:2609.21597},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21597},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2116dcaaba91; sha256 92e87e8f32fc7bcf3987b22d9b6e39ca2f4c2d5b3c1c5093fb7ef14d949cd519},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21597. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Monocular 6-DoF pose estimation of non-cooperative targets is important for on-orbit servicing and debris removal. A single-image estimator can confuse near-symmetric spacecraft orientations, and tracking can preserve an incorrect pose. We present Hypothesis-Anchored Tracking (HAT), a causal framework that uses inter-frame motion to select among competing CAD-based pose hypotheses before alignment and fusion. Rather than independently choosing the highest-scoring hypothesis in each image, HAT retains competing orientation histories and selects a pose to anchor the relative trajectory estimated by monocular SLAM. Sparse anchors and pose fusion provide per-frame estimates after initialization without revising past outputs. The method requires only a calibrated RGB sequence, a metric CAD model, and target image regions, which can be supplied by detection or segmentation. The pretrained pose and SLAM networks require no target-specific training or fine-tuning. We evaluate two versions, Mega-HAT and Pico-HAT, using MegaPose and PicoPose, on SPARK-2024, SwissCube and SHIRT, with YCB-Video assessing performance outside the space domain. Using one temporal configuration per method, the arithmetic means of the four dataset-wise comparisons show 9.4% lower mean pose error and 3.76 times the sustained input FPS for Mega-HAT relative to independent MegaPose, and 23.9% lower mean pose error and 2.42 times the FPS for Pico-HAT relative to independent PicoPose. Mega-HAT ablations on SPARK and an offline reference examine component contributions and the effect of revising past estimates.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21597 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T02:07:36.082Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).