Metraipolis › archive › dc_4550bb6d2ab7

SatoyamaCT: A Multi-Axis Night-IR Camera-Trap Benchmark for Monitoring Crop-Damaging Wildlife in Japanese Agroforestry — arXiv:2609.30278

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30278
License (as archived)
CC0-1.0
Archived
2026-10-08T04:15:14.741Z
SHA-256 of the archived text
78de1fbace7a294eb3e63aaf76394ddb45d0a06327f31f5fa9bee59d905eded5
Stable URL of this page
https://metraipolis.com/documento/dc_4550bb6d2ab7

How to cite

SatoyamaCT: A Multi-Axis Night-IR Camera-Trap Benchmark for Monitoring Crop-Damaging Wildlife in Japanese Agroforestry — arXiv:2609.30278 — arXiv (en), https://arxiv.org/abs/2609.30278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4550bb6d2ab7 (Metraipolis archive dc_4550bb6d2ab7, sha256 78de1fbace7a294eb3e63aaf76394ddb45d0a06327f31f5fa9bee59d905eded5)
BibTeX
@misc{dc4550bb6d2ab7,
  title = {SatoyamaCT: A Multi-Axis Night-IR Camera-Trap Benchmark for Monitoring Crop-Damaging Wildlife in Japanese Agroforestry — arXiv:2609.30278},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30278},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4550bb6d2ab7; sha256 78de1fbace7a294eb3e63aaf76394ddb45d0a06327f31f5fa9bee59d905eded5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Crop and forest damage from sika deer, wild boar, and Japanese macaque is a serious economic problem in Japanese satoyama, where farmland and forest intermingle. Camera traps enable scalable monitoring, yet existing benchmarks evaluate recognition in-distribution, rarely prioritize night infrared imagery, and do not jointly address regional domain shift, novel-species detection, and uncertainty-based triage on a single dataset. We introduce the Satoyama Camera Trap Dataset (SatoyamaCT), 12,642 expert-verified crops from night-IR-dominant camera traps across three satoyama regions. An iterative annotation protocol combining BioCLIP embeddings with confidence-ordered confirmation reduced expert effort while all labels were verified by domain ecologists; species-level inter-annotator agreement reached Cohen's kappa = 0.900. A multi-axis protocol jointly evaluates domain generalization across region, camera placement, and illumination; open-set novel-species detection; and selective prediction, all under capture-event-based leakage control. Difficulty separates into distinct failure modes: a data-inherent regional gap of 16 to 27 percentage points persists in Wakayama across four backbones and domain-generalization methods including CORAL, DANN, and GroupDRO, and open-set detection reaches AUROC 0.93 to 0.96 overall yet degrades jointly with classification in Wakayama. Selective prediction recovers Wakayama accuracy from 0.593 to 0.815 at 50% coverage, supporting an uncertainty-aware triage workflow for practical pest monitoring in agroforestry.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-09-28 in q-bio.QM).
Categorie arXiv: Image and Video Processing (eess.IV) ; Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2609.30278 — 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 2026-10-08T03:47:16.580Z dalla pagina https://arxiv.org/catchup/q-bio.QM/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).