EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Non-Intrusive Water Surface Velocity Measurement Based on Deep Learning

Guocheng An, Tiantian Du, Jin He, Yanwei Zhang

Water · 30.09.2024 · 16 (19) · 2784

DOI: 10.3390/w16192784 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water, online erschienen am 30.09.2024. Verfasst von Guocheng An und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate assessment of water surface velocity (WSV) is essential for flood prevention, disaster mitigation, and erosion control within hydrological monitoring. Existing image-based velocimetry techniques largely depend on correlation principles, requiring users to input and adjust parameters to achieve reliable results, which poses challenges for users lacking relevant expertise. This study presents RivVideoFlow, a user-friendly, rapid, and precise method for WSV. RivVideoFlow combines two-dimensional and three-dimensional orthorectification based on Ground Control Points (GCPs) with a deep learning-based multi-frame optical flow estimation algorithm named VideoFlow, which integrates temporal cues. The orthorectification process employs a homography matrix to convert images from various angles into a top-down view, aligning the image coordinates with actual geographical coordinates. VideoFlow achieves superior accuracy and strong dataset generalization compared to two-frame RAFT models due to its more effective capture of flow velocity continuity over time, leading to enhanced stability in velocity measurements. The algorithm has been validated on a flood simulation experimental platform, in outdoor settings, and with synthetic river videos. Results demonstrate that RivVideoFlow can robustly estimate surface velocity under various camera perspectives, enabling continuous real-time dynamic measurement of the entire flow field. Moreover, RivVideoFlow has demonstrated superior performance in low, medium, and high flow velocity scenarios, especially in high-velocity conditions where it achieves high measurement precision. This method provides a more effective solution for hydrological monitoring.

Förderung

  • National Key R&D Program of China

Zitieren

APA

An, G., Du, T., He, J., & Zhang, Y. (2024). Non-Intrusive Water Surface Velocity Measurement Based on Deep Learning. Water, 16(19), 2784. https://doi.org/10.3390/w16192784

Vancouver

An G, Du T, He J, Zhang Y. Non-Intrusive Water Surface Velocity Measurement Based on Deep Learning. Water. 2024;16(19):2784. doi:10.3390/w16192784

BibTeX
@article{An2024,
  author = {An, Guocheng and Du, Tiantian and He, Jin and Zhang, Yanwei},
  title = {Non-Intrusive Water Surface Velocity Measurement Based on Deep Learning},
  journal = {Water},
  year = {2024},
  volume = {16},
  number = {19},
  pages = {2784},
  doi = {10.3390/w16192784}
}
Kostenlos starten →