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

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 lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Jonathan Gregory, Scott M. Miehls, Jesse L. Eickholt, Daniel P. Zielinski
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/4/1022
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850082596945395712
author Jonathan Gregory
Scott M. Miehls
Jesse L. Eickholt
Daniel P. Zielinski
author_facet Jonathan Gregory
Scott M. Miehls
Jesse L. Eickholt
Daniel P. Zielinski
author_sort Jonathan Gregory
collection DOAJ
description 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.
format Article
id doaj-art-ca9fb4fd5e49462ebb30599530bde753
institution DOAJ
issn 1424-8220
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-ca9fb4fd5e49462ebb30599530bde7532025-08-20T02:44:29ZengMDPI AGSensors1424-82202025-02-01254102210.3390/s25041022A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish PassageJonathan Gregory0Scott M. Miehls1Jesse L. Eickholt2Daniel P. Zielinski3Department of Computer Science, Central Michigan University, Mount Pleasant, MI 48859, USAU.S. Geological Survey, Great Lakes Science Center, Hammond Bay Biological Station, Millersburg, MI 49759, USADepartment of Computer Science, Central Michigan University, Mount Pleasant, MI 48859, USAGreat Lakes Fishery Commission, Ann Arbor, MI 48105, USARecent 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.https://www.mdpi.com/1424-8220/25/4/1022selective fish passageobject detectionedge computingMobileNet SSDreal-time detection
spellingShingle Jonathan Gregory
Scott M. Miehls
Jesse L. Eickholt
Daniel P. Zielinski
A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
Sensors
selective fish passage
object detection
edge computing
MobileNet SSD
real-time detection
title A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
title_full A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
title_fullStr A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
title_full_unstemmed A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
title_short A Real-Time Fish Detection System for Partially Dewatered Fish to Support Selective Fish Passage
title_sort real time fish detection system for partially dewatered fish to support selective fish passage
topic selective fish passage
object detection
edge computing
MobileNet SSD
real-time detection
url https://www.mdpi.com/1424-8220/25/4/1022
work_keys_str_mv AT jonathangregory arealtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT scottmmiehls arealtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT jesseleickholt arealtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT danielpzielinski arealtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT jonathangregory realtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT scottmmiehls realtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT jesseleickholt realtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage
AT danielpzielinski realtimefishdetectionsystemforpartiallydewateredfishtosupportselectivefishpassage