A dual underwater camera system connected, synchronized and powered via cable to a waterproof transportable computer, was developed. This device was used for acquiring tuna images during the transfer from fishing net to a floating cage, thus validating the potential advantages of the use of underwater video monitoring. Two images per second were recorded during tuna transfer and stored for biometric analyses, which were carried out by means of a software tool based on Artificial Neural Networks (ANNs). The ANN was trained to convert distance between pixels in each pair of images into distance between points in the real objects, automatically correcting the estimates for distance from the cameras and aspect. The ANN-based software tool allowed analysing tuna transfer images, providing biometric information of about 1000 tunas. The results were compared to conventional assessment methods. (C) 2009 Elsevier B.V. All rights reserved.
Costa, C., Scardi, M., Vitalini, V., Cataudella, S. (2009). A dual camera system for counting and sizing Northern Bluefin Tuna (Thunnus thynnus; Linnaeus, 1758) stock, during transfer to aquaculture cages, with a semi automatic Artificial Neural Network tool. AQUACULTURE, 291, 161-167 [10.1016/j.aquaculture.2009.02.013].
A dual camera system for counting and sizing Northern Bluefin Tuna (Thunnus thynnus; Linnaeus, 1758) stock, during transfer to aquaculture cages, with a semi automatic Artificial Neural Network tool
SCARDI, MICHELE;CATAUDELLA, STEFANO
2009-01-01
Abstract
A dual underwater camera system connected, synchronized and powered via cable to a waterproof transportable computer, was developed. This device was used for acquiring tuna images during the transfer from fishing net to a floating cage, thus validating the potential advantages of the use of underwater video monitoring. Two images per second were recorded during tuna transfer and stored for biometric analyses, which were carried out by means of a software tool based on Artificial Neural Networks (ANNs). The ANN was trained to convert distance between pixels in each pair of images into distance between points in the real objects, automatically correcting the estimates for distance from the cameras and aspect. The ANN-based software tool allowed analysing tuna transfer images, providing biometric information of about 1000 tunas. The results were compared to conventional assessment methods. (C) 2009 Elsevier B.V. All rights reserved.File | Dimensione | Formato | |
---|---|---|---|
tuna_transfer.pdf
solo utenti autorizzati
Descrizione: Main article
Licenza:
Creative commons
Dimensione
1.17 MB
Formato
Adobe PDF
|
1.17 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Questo articolo è pubblicato sotto una Licenza Licenza Creative Commons