Image-Based Method for Automatic Spillway Ruler Reading
IEEE Access · 2026 · 14 · 68910-68919
DOI: 10.1109/access.2026.3688802 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Alexandre Schviderski und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-CAPES (ROR identifier: 00xma614) for the article processing fee.
Abstract (Originalsprache)
Spillway gates are critical structures in hydroelectric power plants, having a huge impact on the environment and demanding careful monitoring whenever they are maneuvered. In this work, we propose an approach to automatically infer the aperture value of the gates, employing deep learning and traditional computer vision techniques on frames captured by cameras that are commonly used to remotely monitor the maneuvers. We employ a fine-tuned YOLO11 model to detect both the numerical markers and the pointer present in the scene, obtaining information to estimate the curvature of the ruler used to measure gate openings, rectify the image so that the ruler appears vertical and straight, and refine the position of the pointer tip that indicates the measured value. The proposed approach was evaluated on a dataset containing 27,194 images captured under real-world operating conditions by 24 cameras showing three different ruler types, which is freely available for research purposes. Our approach achieved a median error of 6.23 cm compared with ground-truth aperture annotations for rulers whose openings can reach 16 m, demonstrating the method’s potential to support operators performing remote maneuvers via camera systems. To the best of the authors’ knowledge, and based on the experience of professionals in the field, this is the first work proposing the automatic reading of spillway rulers considering the characteristics of the real-world application scenario, without modifications to the existing infrastructure.
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-CAPES (ROR identifier: 00xma614) for the article processing fee
Zitieren
APA
Schviderski, A., & Nassu, B. T. (2026). Image-Based Method for Automatic Spillway Ruler Reading. IEEE Access, 14, 68910-68919. https://doi.org/10.1109/access.2026.3688802
Vancouver
Schviderski A, Nassu BT. Image-Based Method for Automatic Spillway Ruler Reading. IEEE Access. 2026;14:68910-68919. doi:10.1109/access.2026.3688802
BibTeX
@article{Schviderski2026,
author = {Schviderski, Alexandre and Nassu, Bogdan Tomoyuki},
title = {Image-Based Method for Automatic Spillway Ruler Reading},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {68910--68919},
doi = {10.1109/access.2026.3688802}
}
EUVIMED