EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage

Jonathan Gregory iD, Scott M Miehls iD, Jesse L Eickholt, Daniel P Zielinski iD

Sensors · 2025

DOI: 10.3390/s25041022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Jonathan Gregory und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Central Michigan University, Mount Pleasant, MI 48859, USA. Hauptthemen laut MEDLINE: Fishes. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Great Lakes Fishery Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in fish transportation technologies and deep machine learning-based fish classification have created an opportunity for real-time, autonomous fish sorting through a selective passage mechanism. This research presents a case study of a novel application that utilizes deep machine learning to detect partially dewatered fish exiting an Archimedes Screw Fish Lift (ASFL). A MobileNet SSD model was trained on images of partially dewatered fish volitionally passing through an ASFL. Then, this model was integrated with a network video recorder to monitor video from the ASFL. Additional models were also trained using images from a similar fish scanning device to test the feasibility of this approach for fish classification. Open source software and edge computing design principles were employed to ensure that the system is capable of fast data processing. The findings from this research demonstrate that such a system integrated with an ASFL can support real-time fish detection. This research contributes to the goal of automated data collection in a selective fish passage system and presents a viable path towards realizing optical fish sorting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FishesAnimalsVideo RecordingDeep LearningImage Processing, Computer-AssistedMachine LearningSoftware

Stichwörter der Autor:innen

MobileNet SSDedge computingobject detectionreal-time detectionselective fish passage

Autor:innen und Institutionen

  • Department of Computer Science, Central Michigan University, Mount Pleasant, MI 48859, USA.
  • U.S. Geological Survey, Great Lakes Science Center, Hammond Bay Biological Station, Millersburg, MI 49759, USA.
  • Great Lakes Fishery Commission, Ann Arbor, MI 48105, USA.

ORCID-Profile: Jonathan Gregory, Scott M Miehls, Daniel P Zielinski

Förderung

  • Great Lakes Fishery Commission

Zitieren

APA

Gregory, J., Miehls, S. M., Eickholt, J. L., & Zielinski, D. P. (2025). A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage. Sensors. https://doi.org/10.3390/s25041022

Vancouver

Gregory J, Miehls SM, Eickholt JL, Zielinski DP. A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage. Sensors. 2025. doi:10.3390/s25041022

BibTeX
@article{Gregory2025,
  author = {Gregory, Jonathan and Miehls, Scott M and Eickholt, Jesse L and Zielinski, Daniel P},
  title = {A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25041022}
}
Kostenlos starten →