Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow

Kazuki FUKAE; Tetsuo IMAI; Kenichi ARAI; Toru KOBAYASHI

doi:10.1587/transinf.2022OFP0003

Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow

Kazuki FUKAE, Tetsuo IMAI, Kenichi ARAI, Toru KOBAYASHI

Full Text Views

0

Cite this

Summary :

With the growing global demand for seafood, sustainable aquaculture is attracting more attention than conventional natural fishing, which causes overfishing and damage to the marine environment. However, a major problem facing the aquaculture industry is the cost of feeding, which accounts for about 60% of a fishing expenditure. Excessive feeding increases costs, and the accumulation of residual feed on the seabed negatively impacts the quality of water environments (e.g., causing red tides). Therefore, the importance of raising fishes efficiently with less food by optimizing the timing and quantity of feeding becomes more evident. Thus, we developed a system to quantitate the amount of fish activity for the optimal feeding time and feed quantity based on the images taken. For quantitation, optical flow that is a method for tracking individual objects was used. However, it is difficult to track individual fish and quantitate their activity in the presence of many fishes. Therefore, all fish in the filmed screen were considered as a single school and the amount of change in an entire screen was used as the amount of the school activity. We divided specifically the entire image into fixed regions and quantitated by vectorizing the amount of change in each region using optical flow. A vector represents the moving distance and direction. We used the numerical data of a histogram as the indicator for the amount of fish activity by dividing them into classes and recording the number of occurrences in each class. We verified the effectiveness of the indicator by quantitating the eating and not eating movements during feeding. We evaluated the performance of the quantified indicators by the support vector classification, which is a form of machine learning. We confirmed that the two activities can be correctly classified.

Publication: IEICE TRANSACTIONS on Information Vol.E106-D No.9 pp.1472-1479

Publication Date: 2023/09/01

Publicized: 2023/06/20

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2022OFP0003

Type of Manuscript: Special Section PAPER (Special Section on Log Data Usage Technology and Office Information Systems)

Category

Authors

Kazuki FUKAE
  Nagasaki University
Tetsuo IMAI
  Hiroshima City University
Kenichi ARAI
  Nagasaki University
Toru KOBAYASHI
  Nagasaki University

Keyword

optical flow, machine learning, aquaclture, fisheries engineering

Cite this

Copy

Kazuki FUKAE, Tetsuo IMAI, Kenichi ARAI, Toru KOBAYASHI, "Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow" in IEICE TRANSACTIONS on Information, vol. E106-D, no. 9, pp. 1472-1479, September 2023, doi: 10.1587/transinf.2022OFP0003.
Abstract: With the growing global demand for seafood, sustainable aquaculture is attracting more attention than conventional natural fishing, which causes overfishing and damage to the marine environment. However, a major problem facing the aquaculture industry is the cost of feeding, which accounts for about 60% of a fishing expenditure. Excessive feeding increases costs, and the accumulation of residual feed on the seabed negatively impacts the quality of water environments (e.g., causing red tides). Therefore, the importance of raising fishes efficiently with less food by optimizing the timing and quantity of feeding becomes more evident. Thus, we developed a system to quantitate the amount of fish activity for the optimal feeding time and feed quantity based on the images taken. For quantitation, optical flow that is a method for tracking individual objects was used. However, it is difficult to track individual fish and quantitate their activity in the presence of many fishes. Therefore, all fish in the filmed screen were considered as a single school and the amount of change in an entire screen was used as the amount of the school activity. We divided specifically the entire image into fixed regions and quantitated by vectorizing the amount of change in each region using optical flow. A vector represents the moving distance and direction. We used the numerical data of a histogram as the indicator for the amount of fish activity by dividing them into classes and recording the number of occurrences in each class. We verified the effectiveness of the indicator by quantitating the eating and not eating movements during feeding. We evaluated the performance of the quantified indicators by the support vector classification, which is a form of machine learning. We confirmed that the two activities can be correctly classified.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022OFP0003/_p

Copy

@ARTICLE{e106-d_9_1472,
author={Kazuki FUKAE, Tetsuo IMAI, Kenichi ARAI, Toru KOBAYASHI, },
journal={IEICE TRANSACTIONS on Information},
title={Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow},
year={2023},
volume={E106-D},
number={9},
pages={1472-1479},
abstract={With the growing global demand for seafood, sustainable aquaculture is attracting more attention than conventional natural fishing, which causes overfishing and damage to the marine environment. However, a major problem facing the aquaculture industry is the cost of feeding, which accounts for about 60% of a fishing expenditure. Excessive feeding increases costs, and the accumulation of residual feed on the seabed negatively impacts the quality of water environments (e.g., causing red tides). Therefore, the importance of raising fishes efficiently with less food by optimizing the timing and quantity of feeding becomes more evident. Thus, we developed a system to quantitate the amount of fish activity for the optimal feeding time and feed quantity based on the images taken. For quantitation, optical flow that is a method for tracking individual objects was used. However, it is difficult to track individual fish and quantitate their activity in the presence of many fishes. Therefore, all fish in the filmed screen were considered as a single school and the amount of change in an entire screen was used as the amount of the school activity. We divided specifically the entire image into fixed regions and quantitated by vectorizing the amount of change in each region using optical flow. A vector represents the moving distance and direction. We used the numerical data of a histogram as the indicator for the amount of fish activity by dividing them into classes and recording the number of occurrences in each class. We verified the effectiveness of the indicator by quantitating the eating and not eating movements during feeding. We evaluated the performance of the quantified indicators by the support vector classification, which is a form of machine learning. We confirmed that the two activities can be correctly classified.},
keywords={},
doi={10.1587/transinf.2022OFP0003},
ISSN={1745-1361},
month={September},}

Copy

TY - JOUR
TI - Fish School Behaviour Classification for Optimal Feeding Using Dense Optical Flow
T2 - IEICE TRANSACTIONS on Information
SP - 1472
EP - 1479
AU - Kazuki FUKAE
AU - Tetsuo IMAI
AU - Kenichi ARAI
AU - Toru KOBAYASHI
PY - 2023
DO - 10.1587/transinf.2022OFP0003
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2023
AB - With the growing global demand for seafood, sustainable aquaculture is attracting more attention than conventional natural fishing, which causes overfishing and damage to the marine environment. However, a major problem facing the aquaculture industry is the cost of feeding, which accounts for about 60% of a fishing expenditure. Excessive feeding increases costs, and the accumulation of residual feed on the seabed negatively impacts the quality of water environments (e.g., causing red tides). Therefore, the importance of raising fishes efficiently with less food by optimizing the timing and quantity of feeding becomes more evident. Thus, we developed a system to quantitate the amount of fish activity for the optimal feeding time and feed quantity based on the images taken. For quantitation, optical flow that is a method for tracking individual objects was used. However, it is difficult to track individual fish and quantitate their activity in the presence of many fishes. Therefore, all fish in the filmed screen were considered as a single school and the amount of change in an entire screen was used as the amount of the school activity. We divided specifically the entire image into fixed regions and quantitated by vectorizing the amount of change in each region using optical flow. A vector represents the moving distance and direction. We used the numerical data of a histogram as the indicator for the amount of fish activity by dividing them into classes and recording the number of occurrences in each class. We verified the effectiveness of the indicator by quantitating the eating and not eating movements during feeding. We evaluated the performance of the quantified indicators by the support vector classification, which is a form of machine learning. We confirmed that the two activities can be correctly classified.
ER -