EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mechanism-Constrained Synthetic Data for Detection-Oriented Visual Sensing of Analog Gauges Under Limited Pointer Annotation

Qirui Li, Haiyang Luo, Zhiping Peng, Delong Cui, Gen Liang, Yong Ke, Yajing Zhang

Sensors · 13.11.2026 · 26 (22) · 7185

DOI: 10.3390/s26227185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 13.11.2026. Verfasst von Qirui Li und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic analog-gauge interpretation is constrained by the cost of pointer-level annotation and by limited coverage of rare operating states. This work presents a mechanism-constrained synthetic-data framework (B-data) for detection-oriented gauge sensing under limited pointer supervision. Six real seed templates are decomposed into dial and pointer assets, deterministically re-centered to a common pivot, and synthesized by sampling only within template-specific valid angular intervals. A same-budget unconstrained control uses the same assets, perturbations, and 6000-image budget but samples over the full 360∘ range. The theoretical valid-arc coverage of unconstrained rotation is 54.91%, and the observed rate is 54.97% (3298/6000), whereas B-data achieves 100% valid-arc compliance. Under the principal setting, in which pointer boxes are available for 25% of the 422 real training images, B-data reaches 62.8 ± 2.2% pointer AP@0.5 across three independent training seeds on a 100-image independent test set from 18 unseen instruments, compared with 54.9 ± 2.5% for unconstrained synthesis and 47.6 ± 2.8% for real-only training. B-data also increases geometry-consistent output to 40.3 ± 1.5%, reduces conditional angular MAE to 5.2 ± 0.7∘, and raises end-to-end ≤10∘ success to 35.7 ± 1.5%. These results show that valid-state constraints provide transferable structural supervision beyond synthetic-data quantity alone. The resulting 6000-image mechanism-constrained B-data release, including paired detection annotations and generation metadata, is publicly available on Zenodo.

Zitieren

APA

Li, Q., Luo, H., Peng, Z., Cui, D., Liang, G., Ke, Y., & Zhang, Y. (2026). Mechanism-Constrained Synthetic Data for Detection-Oriented Visual Sensing of Analog Gauges Under Limited Pointer Annotation. Sensors, 26(22), 7185. https://doi.org/10.3390/s26227185

Vancouver

Li Q, Luo H, Peng Z, Cui D, Liang G, Ke Y, et al. Mechanism-Constrained Synthetic Data for Detection-Oriented Visual Sensing of Analog Gauges Under Limited Pointer Annotation. Sensors. 2026;26(22):7185. doi:10.3390/s26227185

BibTeX
@article{Li2026,
  author = {Li, Qirui and Luo, Haiyang and Peng, Zhiping and Cui, Delong and Liang, Gen and Ke, Yong and Zhang, Yajing},
  title = {Mechanism-Constrained Synthetic Data for Detection-Oriented Visual Sensing of Analog Gauges Under Limited Pointer Annotation},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7185},
  doi = {10.3390/s26227185}
}
Kostenlos starten →