Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm
DIDSON acoustic cameras provide a way to collect temporally dense, high-resolution imaging data, similar to videos. Detection of fish targets on those videos takes place in a manual or semi-automated manner, typically assisted by specialised software. Exploiting the visual nature of the recordings,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/9/1304 |
| _version_ | 1797534998722510848 |
|---|---|
| author | Triantafyllia-Maria Perivolioti Michal Tušer Dimitrios Terzopoulos Stefanos P. Sgardelis Ioannis Antoniou |
| author_facet | Triantafyllia-Maria Perivolioti Michal Tušer Dimitrios Terzopoulos Stefanos P. Sgardelis Ioannis Antoniou |
| author_sort | Triantafyllia-Maria Perivolioti |
| collection | DOAJ |
| description | DIDSON acoustic cameras provide a way to collect temporally dense, high-resolution imaging data, similar to videos. Detection of fish targets on those videos takes place in a manual or semi-automated manner, typically assisted by specialised software. Exploiting the visual nature of the recordings, tools and techniques from the field of computer vision can be applied in order to facilitate the relatively involved workflows. Furthermore, machine learning techniques can be used to minimise user intervention and optimise for specific detection and tracking scenarios. This study explored the feasibility of combining optical flow with a genetic algorithm, with the aim of automating motion detection and optimising target-to-background segmentation (masking) under custom criteria, expressed in terms of the result. A 1000-frame video sequence sample with sparse, smoothly moving targets, reconstructed from a 125 s DIDSON recording, was analysed under two distinct scenarios, and an elementary detection method was used to assess and compare the resulting foreground (target) masks. The results indicate a high sensitivity to motion, as well as to the visual characteristics of targets, with the resulting foreground masks generally capturing fish targets on the majority of frames, potentially with small gaps of undetected targets, lasting for no more than a few frames. Despite the high computational overhead, implementation refinements could increase computational feasibility, while an extension of the algorithms, in order to include the steps of target detection and tracking, could further improve automation and potentially provide an efficient tool for the automated preliminary assessment of voluminous DIDSON data recordings. |
| first_indexed | 2024-03-10T11:38:22Z |
| format | Article |
| id | doaj.art-36d238bbac0b4a2b82b60829fc0e8e02 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T11:38:22Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-36d238bbac0b4a2b82b60829fc0e8e022023-11-21T18:41:53ZengMDPI AGWater2073-44412021-05-01139130410.3390/w13091304Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic AlgorithmTriantafyllia-Maria Perivolioti0Michal Tušer1Dimitrios Terzopoulos2Stefanos P. Sgardelis3Ioannis Antoniou4Department of Zoology, School of Biology, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceBiology Centre of the Czech Academy of Sciences, Institute of Hydrobiology, 37005 České Budějovice, Czech RepublicDepartment of Physical and Environmental Geography, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceDepartment of Ecology, School of Biology, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceDepartment of Statistics and Operational Research, Faculty of Sciences, School of Mathematics, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceDIDSON acoustic cameras provide a way to collect temporally dense, high-resolution imaging data, similar to videos. Detection of fish targets on those videos takes place in a manual or semi-automated manner, typically assisted by specialised software. Exploiting the visual nature of the recordings, tools and techniques from the field of computer vision can be applied in order to facilitate the relatively involved workflows. Furthermore, machine learning techniques can be used to minimise user intervention and optimise for specific detection and tracking scenarios. This study explored the feasibility of combining optical flow with a genetic algorithm, with the aim of automating motion detection and optimising target-to-background segmentation (masking) under custom criteria, expressed in terms of the result. A 1000-frame video sequence sample with sparse, smoothly moving targets, reconstructed from a 125 s DIDSON recording, was analysed under two distinct scenarios, and an elementary detection method was used to assess and compare the resulting foreground (target) masks. The results indicate a high sensitivity to motion, as well as to the visual characteristics of targets, with the resulting foreground masks generally capturing fish targets on the majority of frames, potentially with small gaps of undetected targets, lasting for no more than a few frames. Despite the high computational overhead, implementation refinements could increase computational feasibility, while an extension of the algorithms, in order to include the steps of target detection and tracking, could further improve automation and potentially provide an efficient tool for the automated preliminary assessment of voluminous DIDSON data recordings.https://www.mdpi.com/2073-4441/13/9/1304acoustic imagingcomputer visionhydroacousticsfisheries researchimage segmentationimage classification |
| spellingShingle | Triantafyllia-Maria Perivolioti Michal Tušer Dimitrios Terzopoulos Stefanos P. Sgardelis Ioannis Antoniou Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm Water acoustic imaging computer vision hydroacoustics fisheries research image segmentation image classification |
| title | Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm |
| title_full | Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm |
| title_fullStr | Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm |
| title_full_unstemmed | Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm |
| title_short | Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm |
| title_sort | optimising the workflow for fish detection in didson dual frequency identification sonar data with the use of optical flow and a genetic algorithm |
| topic | acoustic imaging computer vision hydroacoustics fisheries research image segmentation image classification |
| url | https://www.mdpi.com/2073-4441/13/9/1304 |
| work_keys_str_mv | AT triantafylliamariaperivolioti optimisingtheworkflowforfishdetectionindidsondualfrequencyidentificationsonardatawiththeuseofopticalflowandageneticalgorithm AT michaltuser optimisingtheworkflowforfishdetectionindidsondualfrequencyidentificationsonardatawiththeuseofopticalflowandageneticalgorithm AT dimitriosterzopoulos optimisingtheworkflowforfishdetectionindidsondualfrequencyidentificationsonardatawiththeuseofopticalflowandageneticalgorithm AT stefanospsgardelis optimisingtheworkflowforfishdetectionindidsondualfrequencyidentificationsonardatawiththeuseofopticalflowandageneticalgorithm AT ioannisantoniou optimisingtheworkflowforfishdetectionindidsondualfrequencyidentificationsonardatawiththeuseofopticalflowandageneticalgorithm |