BFNet: A real-time edge-deployable dual-stream boundary-aware network for defect detection of aquatic photovoltaic systems
Applied Intelligence · 2026-04 · 56 (6)
DOI: 10.1007/s10489-026-07228-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Intelligence, online erschienen am 20.04.2026. Verfasst von Mingyu Zhang und 8 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben.
Abstract (Originalsprache)
In the industrial inspection of aquatic photovoltaic (PV) systems, semantic segmentation faces two critical challenges: the extremely low proportion of defect pixels relative to the overall image and the restrictive edge deployment conditions, which necessitate real-time inference on resource-limited devices. This paper introduces BFNet, a boundary-aware architecture employing a dual-stream design to distinctly separate boundary features from semantic representations, thereby addressing the gradient dominance issue caused by majority classes. The main contributions include: (1) a learnable boundary gating mechanism for adaptive edge enhancement; (2) Dilated Dense Blocks that significantly reduce parameter volume while preserving receptive field coverage; and (3) a multi-task training approach weighted by inverse square root frequency. Experimental evaluations demonstrate that BFNet achieves defect detection accuracy statistically comparable to heavyweight methods, yet with substantially fewer parameters, enabling real-time deployment on battery-powered unmanned surface vessels.
Zitieren
APA
Zhang, M., Cui, J., Zhao, Z., Fang, E., Liu, X., Zhao, S., Gao, J., Hong, Y., & Li, M. (2026). BFNet: A real-time edge-deployable dual-stream boundary-aware network for defect detection of aquatic photovoltaic systems. Applied Intelligence, 56(6). https://doi.org/10.1007/s10489-026-07228-8
Vancouver
Zhang M, Cui J, Zhao Z, Fang E, Liu X, Zhao S, et al. BFNet: A real-time edge-deployable dual-stream boundary-aware network for defect detection of aquatic photovoltaic systems. Applied Intelligence. 2026;56(6). doi:10.1007/s10489-026-07228-8
BibTeX
@article{Zhang2026,
author = {Zhang, Mingyu and Cui, Jiacheng and Zhao, Zizhen and Fang, Erchao and Liu, Xiaolei and Zhao, Shinan and Gao, Jianlin and Hong, Yujiang and Li, Mingxi},
title = {BFNet: A real-time edge-deployable dual-stream boundary-aware network for defect detection of aquatic photovoltaic systems},
journal = {Applied Intelligence},
year = {2026},
volume = {56},
number = {6},
doi = {10.1007/s10489-026-07228-8}
}
EUVIMED