Metraipolis › archive › dc_5198b9bb720e

NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers — arXiv:2609.25022

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25022
License (as archived)
CC0-1.0
Archived
2026-10-08T14:37:36.556Z
SHA-256 of the archived text
a846f4424eab06fcd87cc4bb23185d0bb6f417889491b34bcadd1ce46f7b493c
Stable URL of this page
https://metraipolis.com/documento/dc_5198b9bb720e

How to cite

NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers — arXiv:2609.25022 — arXiv (en), https://arxiv.org/abs/2609.25022 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5198b9bb720e (Metraipolis archive dc_5198b9bb720e, sha256 a846f4424eab06fcd87cc4bb23185d0bb6f417889491b34bcadd1ce46f7b493c)
BibTeX
@misc{dc5198b9bb720e,
  title = {NPLSD: Accelerating Line-Segment Detection on NPU Microcontrollers — arXiv:2609.25022},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25022},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5198b9bb720e; sha256 a846f4424eab06fcd87cc4bb23185d0bb6f417889491b34bcadd1ce46f7b493c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25022. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Line-segment detection is fundamental to robotics, autonomous navigation, and industrial inspection. While transformer-based detectors achieve the highest accuracy, their deployment on microcontrollers remains impractical due to resource constraints. The STM32N6, with its Neural-ART NPU, promises to enable deep vision at the extreme edge. However, existing detectors rely on attention, grid-sampling, and normalization, operators that are unsupported by the convolution-oriented NPU. This architectural mismatch is characterized operator by operator: attention, grid-sampling, and normalization lack accelerator primitives, and the decoder's self-attention alone materializes a 39 MB score tensor that exceeds on-chip memory. To address this limitation, NPLSD is introduced as a pair of NPU-compatible line-segment detectors built from one design methodology. NPLSD-H retains the convolutional HGNetv2 backbone of LINEA and replaces the transformer head with a fully-convolutional feature pyramid and an F-Clip dense head. NPLSD-M adapts the M-LSD-tiny trunk to the supported operator set. Warm-started from ImageNet and trained on ShanghaiTech Wireframe, the 2.63M-parameter NPLSD-H reaches sAP^10=37.9 (35.9 int8); the 0.62M-parameter NPLSD-M reaches 41.9 (41.1 int8). A controlled ablation isolates the trunk as the only variable, and initialization alone accounts for 4.6 points.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.25022 — 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 2026-10-08T13:47:52.516Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).