EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Boundary-Aware Semantic Segmentation of Pig Point Clouds in Commercial Housing Environments

Zhankang Xu, Fei Shi, Xiangyu Qi, Zhaoyang Wang, Mengxin Guo, Yikai Fan, Simon X. Yang, Qifeng Li, Weihong Ma

Sensors and AI · 18.11.2026 · 2 (1) · 50-71

DOI: 10.53941/sai.2026.100004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors and AI, online erschienen am 18.11.2026. Verfasst von Zhankang Xu und 8 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, BAAFS Outstanding Scientist Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In commercial pig-housing environments, contact between pig-body point clouds and background structures can produce blurred boundaries, local adhesion, and background misclassification, which may propagate to downstream three-dimensional phenotyping. This study proposes a boundary-aware pig point-cloud segmentation method based on an Octree Transformer backbone. The framework combines multi-scale feature fusion, soft-distance boundary pseudo-labels, and bidirectional semantic-boundary interaction. On the prespecified independent test split, the method achieved an accuracy (Acc) of 98.65%, a mean intersection over union (mIoU) of 97.36%, and a boundary intersection over union (B-IoU of 88.77%. These are single-run point estimates; inferential significance and variability across random initializations were not assessed. The evaluation was intended to examine the complete boundary-aware workflow under a fixed independent animal-level protocol rather than to establish statistical significance from small numerical margins. The observed advantage was largest for B-IoU, consistent with the method’s explicit boundary objective, and should therefore be interpreted together with Acc, mIoU, and qualitative results. The findings support the method under the two sampled farms and fixed acquisition configurations, while cross-farm and cross-device generalization remain to be established.

Förderung

  • Sichuan Science and Technology Program
  • BAAFS Outstanding Scientist Project

Zitieren

APA

Xu, Z., Shi, F., Qi, X., Wang, Z., Guo, M., Fan, Y., Yang, S. X., Li, Q., & Ma, W. (2026). Boundary-Aware Semantic Segmentation of Pig Point Clouds in Commercial Housing Environments. Sensors and AI, 2(1), 50-71. https://doi.org/10.53941/sai.2026.100004

Vancouver

Xu Z, Shi F, Qi X, Wang Z, Guo M, Fan Y, et al. Boundary-Aware Semantic Segmentation of Pig Point Clouds in Commercial Housing Environments. Sensors and AI. 2026;2(1):50-71. doi:10.53941/sai.2026.100004

BibTeX
@article{Xu2026,
  author = {Xu, Zhankang and Shi, Fei and Qi, Xiangyu and Wang, Zhaoyang and Guo, Mengxin and Fan, Yikai and Yang, Simon X. and Li, Qifeng and Ma, Weihong},
  title = {Boundary-Aware Semantic Segmentation of Pig Point Clouds in Commercial Housing Environments},
  journal = {Sensors and AI},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {50--71},
  doi = {10.53941/sai.2026.100004}
}
Kostenlos starten →